[ { "language_name": "English", "bcp_47": "en", "speakers": 1636485840, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.40476391184425853, "mt_chrf": 0.5350771248567329, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9792909796569321, "t2t_score": 0.6936782570601107 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.42039857566100747, "mt_chrf": 0.5300571003447904, "cls_acc": 0.5, "mlm_chrf": 0.9378674673892118, "t2t_score": 0.6559748559113341 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.39023213290403214, "mt_chrf": 0.501310810487581, "cls_acc": 0.43333333333333335, "mlm_chrf": 0.7876173555317149, "t2t_score": 0.5740871664508763 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.5005636231739998, "mt_chrf": 0.6083608181074219, "cls_acc": 0.8666666666666667, "mlm_chrf": 0.9820612175447262, "t2t_score": 0.819029567439605 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.32249653301750936, "asr_chrf": 0.8168177351797856, "s2t_score": 0.5696571340986475 }, { "model": "openai/whisper-large-v3", "model_type": "speech-to-text", "asr_wer": 0.25418986127300397, "asr_chrf": 0.8652016887049812, "s2t_score": 0.5596957749889926 } ], "commonvoice_hours": 2651.0, "commonvoice_locale": "en", "population": { "AC": 931, "AE": 4996040, "AG": 84434, "AI": 17186, "AQ": 300, "AR": 3183537, "AS": 47954, "AT": 6467398, "AU": 24447840, "AW": 2986, "BA": 1726016, "BB": 294560, "BD": 29277180, "BE": 6915213, "BG": 1741725, "BI": 6289, "BM": 66010, "BN": 7896, "BR": 16937280, "BS": 337721, "BT": 86055, "BV": 1, "BW": 1876956, "BZ": 399598, "CA": 32416926, "CC": 101, "CH": 5126434, "CK": 8574, "CL": 1727746, "CM": 10543100, "CN": 62731, "CP": 1, "CQ": 482, "CX": 1389, "CY": 924676, "CZ": 2889675, "DE": 51302208, "DG": 495, "DK": 5047693, "DM": 69788, "DO": 7980, "DZ": 3008103, "EE": 614310, "EG": 36443400, "ER": 3587908, "ES": 12003792, "ET": 46488590, "FI": 3900169, "FJ": 879816, "FK": 2814, "FM": 58389, "FR": 26460798, "GB": 64445878, "GD": 108570, "GG": 67052, "GH": 6161442, "GI": 23665, "GM": 869600, "GR": 5409621, "GS": 20, "GU": 153321, "GY": 750204, "HK": 3697454, "HM": 1, "HN": 40635, "HR": 2071598, "HU": 1954366, "IE": 5073039, "IL": 7374158, "IM": 90499, "IN": 251957100, "IO": 3500, "IQ": 13605445, "IT": 21216918, "JE": 96019, "JM": 2752399, "JO": 4869270, "KE": 10170301, "KI": 111796, "KN": 52745, "KY": 60705, "KZ": 2863785, "LB": 2187844, "LC": 149838, "LK": 2288920, "LR": 4210839, "LS": 531719, "LT": 1037955, "LU": 351893, "LV": 865366, "MA": 4978638, "MG": 4852026, "MH": 72463, "MO": 14133, "MP": 49890, "MS": 3492, "MT": 402395, "MU": 993146, "MV": 293928, "MW": 13353858, "MX": 16724500, "MY": 6856941, "NA": 184105, "NF": 1678, "NG": 113434840, "NL": 15552360, "NP": 909837, "NR": 9350, "NU": 1120, "NZ": 4826970, "PA": 545171, "PG": 3629730, "PH": 69875840, "PK": 116750500, "PL": 12633159, "PM": 187, "PN": 46, "PR": 1562644, "PT": 2781729, "PW": 1887, "RO": 6603899, "RW": 1906860, "SB": 685097, "SC": 36473, "SD": 27792576, "SE": 8774150, "SG": 5774984, "SH": 5425, "SI": 1240581, "SK": 1414556, "SL": 2318726, "SS": 2851524, "SX": 29816, "SZ": 883584, "TA": 272, "TC": 54807, "TH": 18623898, "TK": 1285, "TO": 29707, "TR": 13942975, "TT": 1063735, "TV": 1066, "TZ": 40401432, "UG": 1686867, "UM": 316, "US": 319333440, "VC": 97334, "VG": 36633, "VI": 79676, "VU": 247616, "WS": 4279, "YE": 2689596, "ZA": 17503716, "ZM": 2788256, "ZW": 6109446 }, "language_family": "Indo-European", "mt_bleu": 0.42898956089582446, "mt_chrf": 0.5437014634491315, "cls_acc": 0.5916666666666667, "mlm_chrf": 0.9217092550306462, "asr_wer": 0.2883431971452567, "asr_chrf": 0.8410097119423834, "t2t_score": 0.6856924617154815, "s2t_score": 0.5646764545438201 }, { "language_name": "Chinese", "bcp_47": "zh", "speakers": 1304678914, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.37010453186602793, "mt_chrf": 0.5495542857606343, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.900779581057449, "t2t_score": 0.63900017782825 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.3904811079178694, "mt_chrf": 0.5665464429871689, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9044414344868564, "t2t_score": 0.6792181813802306 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.3631466653543813, "mt_chrf": 0.552006597905903, "cls_acc": 0.6666666666666666, "mlm_chrf": 0.8851414000070698, "t2t_score": 0.7012715548598797 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.41028031844473206, "mt_chrf": 0.5607632287491137, "cls_acc": 0.8666666666666667, "mlm_chrf": 0.9353777720326482, "t2t_score": 0.7876025558161427 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 1.0, "asr_chrf": 0.7077419107011705, "s2t_score": 0.8538709553505852 }, { "model": "openai/whisper-large-v3", "model_type": "speech-to-text", "asr_wer": 1.0, "asr_chrf": 0.7748220275963785, "s2t_score": 0.8874110137981892 } ], "commonvoice_hours": 422.0, "commonvoice_locale": "zh-TW", "population": { "AU": 534796, "BN": 51093, "CA": 678494, "CN": 1254618000, "GB": 197283, "GF": 4988, "HK": 7249910, "ID": 2456639, "MN": 44352, "MO": 632892, "MY": 5550857, "PA": 5841, "PF": 23019, "PH": 797021, "SG": 4781438, "SR": 6705, "TH": 1241593, "TW": 22422850, "US": 2295209, "VN": 1085934 }, "language_family": "Sino-Tibetan", "mt_bleu": 0.3835031558957527, "mt_chrf": 0.557217638850705, "cls_acc": 0.6416666666666666, "mlm_chrf": 0.9064350468960058, "asr_wer": 1.0, "asr_chrf": 0.7412819691487745, "t2t_score": 0.7017731174711257, "s2t_score": 0.8706409845743872 }, { "language_name": "Hindi", "bcp_47": "hi", "speakers": 546882144, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.30348099344592144, "mt_chrf": 0.46828573138186164, "cls_acc": 0.5, "mlm_chrf": 0.9491600973221963, "t2t_score": 0.6391486095680193 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.30694468553453214, "mt_chrf": 0.4717417673162039, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9225335146094515, "t2t_score": 0.6536473161974407 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.21739461408317115, "mt_chrf": 0.35902002421447704, "cls_acc": 0.5, "mlm_chrf": 0.8896017448529104, "t2t_score": 0.5828739230224625 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.34270244014502865, "mt_chrf": 0.5241272552859138, "cls_acc": 0.8666666666666667, "mlm_chrf": 0.9648559476590244, "t2t_score": 0.7852166232038682 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.28107684996172205, "asr_chrf": 0.7778871091355449, "s2t_score": 0.5294819795486335 }, { "model": "openai/whisper-large-v3", "model_type": "speech-to-text", "asr_wer": 0.43522263872986894, "asr_chrf": 0.6304928664226873, "s2t_score": 0.5328577525762781 } ], "commonvoice_hours": 16.0, "commonvoice_locale": "hi-IN", "population": { "CA": 188470, "FJ": 411829, "IN": 545022990, "NP": 127377, "UG": 2206, "ZA": 1129272 }, "language_family": "Indo-European", "mt_bleu": 0.29263068330216335, "mt_chrf": 0.45579369454961405, "cls_acc": 0.6083333333333334, "mlm_chrf": 0.9315378261108958, "asr_wer": 0.3581497443457955, "asr_chrf": 0.7041899877791161, "t2t_score": 0.6652216179979477, "s2t_score": 0.5311698660624558 }, { "language_name": "Spanish", "bcp_47": "es", "speakers": 493528077, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.3047910872340331, "mt_chrf": 0.4664322514490113, "cls_acc": 0.6, "mlm_chrf": 0.9773594806492754, "t2t_score": 0.6812639106994288 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2681893620935732, "mt_chrf": 0.4507327709042758, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9387079449855046, "t2t_score": 0.6409246830743712 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.2794753489249633, "mt_chrf": 0.4300653056934316, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.9521615389464084, "t2t_score": 0.6718533926577245 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.34138272852201396, "mt_chrf": 0.5025141961861047, "cls_acc": 0.8666666666666667, "mlm_chrf": 0.9816202595213187, "t2t_score": 0.7836003741246967 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.1927295314766095, "asr_chrf": 0.8941604003451139, "s2t_score": 0.5434449659108617 }, { "model": "openai/whisper-large-v3", "model_type": "speech-to-text", "asr_wer": 0.17561491933862197, "asr_chrf": 0.9185915393819567, "s2t_score": 0.5471032293602893 } ], "commonvoice_hours": 446.0, "commonvoice_locale": "es", "population": { "AD": 33110, "AR": 45479100, "BO": 7100339, "BR": 76218, "BZ": 111887, "CA": 603106, "CL": 17823064, "CO": 45648864, "CR": 4843090, "CU": 11059100, "CW": 5751, "DE": 4809582, "DO": 8189766, "EA": 147000, "EC": 16228704, "ES": 49515642, "FR": 8820266, "GB": 5260888, "GI": 14790, "GQ": 727475, "GT": 15952569, "HN": 7203565, "IC": 2056618, "MA": 23115, "MX": 106779500, "NI": 4838683, "PA": 2686915, "PE": 23297950, "PH": 33846110, "PR": 2774491, "PT": 1030270, "PY": 230134, "RO": 2130290, "SV": 5768179, "SX": 4823, "TT": 4110, "US": 31933344, "UY": 2981097, "VE": 23488572 }, "language_family": "Indo-European", "mt_bleu": 0.29845963169364587, "mt_chrf": 0.4624361310582059, "cls_acc": 0.6583333333333333, "mlm_chrf": 0.9624623060256268, "asr_wer": 0.18417222540761574, "asr_chrf": 0.9063759698635353, "t2t_score": 0.6944105901390554, "s2t_score": 0.5452740976355754 }, { "language_name": "Arabic", "bcp_47": "ar", "speakers": 351664197, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.26593690487060095, "mt_chrf": 0.46048583874582116, "cls_acc": 0.6, "mlm_chrf": 0.9386512881662338, "t2t_score": 0.6663790423040182 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2811587891139184, "mt_chrf": 0.4610903378292814, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9425014853511972, "t2t_score": 0.623419496615715 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.20683544337550522, "mt_chrf": 0.3857194391808861, "cls_acc": 0.7, "mlm_chrf": 0.9148307958510079, "t2t_score": 0.6668500783439647 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.3368489944570755, "mt_chrf": 0.5132383488065384, "cls_acc": 0.9, "mlm_chrf": 0.97921999148367, "t2t_score": 0.7974861134300695 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.2976757980818083, "asr_chrf": 0.8082975812173028, "s2t_score": 0.5529866896495556 }, { "model": "openai/whisper-large-v3", "model_type": "speech-to-text", "asr_wer": 0.17370718156523782, "asr_chrf": 0.8868973505122795, "s2t_score": 0.5303022660387586 } ], "commonvoice_hours": 91.0, "commonvoice_locale": "ar", "population": { "AE": 7793822, "BH": 1309350, "CA": 565412, "CM": 108206, "CY": 1267, "DJ": 67292, "DZ": 31799946, "EG": 97876560, "EH": 652271, "ER": 297979, "GB": 197283, "IL": 1735096, "IQ": 26433436, "IR": 1698466, "JO": 10820600, "KE": 24623, "KM": 558545, "KW": 2993710, "LB": 4703865, "LY": 5099000, "MA": 22048254, "ML": 175981, "MR": 3404658, "NE": 47822, "NG": 151960, "OM": 3778520, "PS": 4818260, "QA": 2175311, "SA": 34173500, "SD": 27792576, "SO": 3997414, "SS": 2851524, "SY": 15518720, "TD": 2869158, "TJ": 976, "TN": 10549080, "TR": 459298, "YE": 22114456 }, "language_family": "Afro-Asiatic", "mt_bleu": 0.272695032954275, "mt_chrf": 0.45513349114063173, "cls_acc": 0.6666666666666666, "mlm_chrf": 0.9438008902130272, "asr_wer": 0.23569148982352306, "asr_chrf": 0.8475974658647911, "t2t_score": 0.6885336826734418, "s2t_score": 0.5416444778441571 }, { "language_name": "Urdu", "bcp_47": "ur", "speakers": 290790290, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.25651711220915696, "mt_chrf": 0.434940424205634, "cls_acc": 0.43333333333333335, "mlm_chrf": 0.9405185966090683, "t2t_score": 0.6029307847160119 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.21847309277555946, "mt_chrf": 0.4036061618297173, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9330700955297437, "t2t_score": 0.6011143080087092 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.18142367436048185, "mt_chrf": 0.3459866651047097, "cls_acc": 0.6666666666666666, "mlm_chrf": 0.9320431438157005, "t2t_score": 0.6482321585290256 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.31728190361318, "mt_chrf": 0.48818783571496116, "cls_acc": 0.9, "mlm_chrf": 0.9548190343172376, "t2t_score": 0.7810022900107328 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.33586677704198, "asr_chrf": 0.7430938264813908, "s2t_score": 0.5394803017616854 } ], "commonvoice_hours": 77.0, "commonvoice_locale": "ur", "population": { "CA": 286475, "GB": 2301638, "IN": 66304500, "MU": 71727, "PK": 221825950 }, "language_family": "Indo-European", "mt_bleu": 0.24342394573959458, "mt_chrf": 0.41818027171375555, "cls_acc": 0.6166666666666667, "mlm_chrf": 0.9401127175679376, "asr_wer": 0.33586677704198, "asr_chrf": 0.7430938264813908, "t2t_score": 0.6583198853161198, "s2t_score": 0.5394803017616854 }, { "language_name": "French", "bcp_47": "fr", "speakers": 278611507, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.3330934985862475, "mt_chrf": 0.48898780285384186, "cls_acc": 0.6666666666666666, "mlm_chrf": 0.9702783834061439, "t2t_score": 0.7086442843088842 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.32618133837885355, "mt_chrf": 0.4952644559037655, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9639910578331403, "t2t_score": 0.6753073934678575 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.27503766788302847, "mt_chrf": 0.441500491331595, "cls_acc": 0.7666666666666667, "mlm_chrf": 0.9709359436365964, "t2t_score": 0.7263677005449528 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.3407733406148989, "mt_chrf": 0.5123861936301051, "cls_acc": 0.8666666666666667, "mlm_chrf": 0.981866385354237, "t2t_score": 0.7869730818836697 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.2610754929736961, "asr_chrf": 0.8775590287945104, "s2t_score": 0.5693172608841033 } ], "commonvoice_hours": 1052.0, "commonvoice_locale": "fr", "population": { "AD": 5775, "AT": 974540, "BE": 4453866, "BF": 4583788, "BI": 7000822, "BJ": 4502610, "BL": 6837, "CA": 11308230, "CD": 3867640, "CF": 2935521, "CG": 4446179, "CH": 1764838, "CI": 13465739, "CM": 18866600, "CY": 88668, "DE": 14428746, "DJ": 19358, "DZ": 8594580, "FR": 67169718, "GA": 1405473, "GB": 15125053, "GF": 153622, "GN": 3632946, "GP": 407498, "GQ": 73584, "GR": 954639, "HT": 520187, "HU": 293155, "IE": 880017, "IT": 3931370, "KM": 473917, "LB": 20238, "LU": 546691, "MA": 7112340, "MC": 38610, "MF": 32556, "MG": 18599433, "ML": 8994564, "MQ": 427408, "MR": 680932, "MT": 50299, "MU": 41381, "NC": 278409, "NE": 6603996, "NL": 5011316, "PF": 180024, "PM": 5133, "PT": 1545405, "RE": 700950, "RO": 3621493, "RW": 2288, "SC": 57589, "SN": 6137196, "SY": 1144506, "TD": 4388124, "TF": 140, "TG": 5251148, "TN": 8673688, "US": 1862778, "VU": 149166, "WF": 7610, "YT": 110580 }, "language_family": "Indo-European", "mt_bleu": 0.3187714613657571, "mt_chrf": 0.4845347359298269, "cls_acc": 0.7166666666666667, "mlm_chrf": 0.9717679425575294, "asr_wer": 0.2610754929736961, "asr_chrf": 0.8775590287945104, "t2t_score": 0.7243231150513411, "s2t_score": 0.5693172608841033 }, { "language_name": "Bangla", "bcp_47": "bn", "speakers": 267193288, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.20957267610789623, "mt_chrf": 0.38143415739652864, "cls_acc": 0.3333333333333333, "mlm_chrf": 0.8956278857774084, "t2t_score": 0.5367984588357567 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.23230854865261916, "mt_chrf": 0.42063939652271853, "cls_acc": 0.36666666666666664, "mlm_chrf": 0.8995877938471141, "t2t_score": 0.5622979523454997 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.17813156872400576, "mt_chrf": 0.34058339171576163, "cls_acc": 0.4, "mlm_chrf": 0.8686306022759065, "t2t_score": 0.5364046646638894 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.29469375187054625, "mt_chrf": 0.4790136299628091, "cls_acc": 0.9, "mlm_chrf": 0.9213788493667834, "t2t_score": 0.7667974931098641 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.3066054718228631, "asr_chrf": 0.8006938100379883, "s2t_score": 0.5536496409304257 } ], "commonvoice_hours": 49.0, "commonvoice_locale": "bn", "population": { "BD": 159397980, "CA": 90466, "GB": 263044, "IN": 107413290, "NP": 28508 }, "language_family": "Indo-European", "mt_bleu": 0.22867663633876686, "mt_chrf": 0.4054176438994545, "cls_acc": 0.5, "mlm_chrf": 0.896306282816803, "asr_wer": 0.3066054718228631, "asr_chrf": 0.8006938100379883, "t2t_score": 0.6005746422387525, "s2t_score": 0.5536496409304257 }, { "language_name": "Portuguese", "bcp_47": "pt", "speakers": 237496885, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.3303753782527083, "mt_chrf": 0.486171419442025, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.976316236530384, "t2t_score": 0.6986069964352475 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2806919135940658, "mt_chrf": 0.4531472771818437, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9630716853128435, "t2t_score": 0.6609618763871179 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.3025841449283074, "mt_chrf": 0.4573560946306324, "cls_acc": 0.6, "mlm_chrf": 0.9304952225388448, "t2t_score": 0.662617105723159 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.37947802751730003, "mt_chrf": 0.534900245316462, "cls_acc": 0.8, "mlm_chrf": 0.9836940585303217, "t2t_score": 0.7728647679489279 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.22800492332171055, "asr_chrf": 0.8922038015648965, "s2t_score": 0.5601043624433035 } ], "commonvoice_hours": 177.0, "commonvoice_locale": "pt", "population": { "AG": 1571, "AO": 21789941, "BR": 192661560, "CA": 229934, "CH": 285736, "CV": 443274, "FR": 882027, "GB": 131522, "GQ": 1, "GW": 1927100, "LU": 100541, "MO": 30723, "MZ": 8126514, "PT": 9890592, "ST": 179454, "TL": 816395 }, "language_family": "Indo-European", "mt_bleu": 0.32328236607309535, "mt_chrf": 0.48289375914274074, "cls_acc": 0.6499999999999999, "mlm_chrf": 0.9633943007280985, "asr_wer": 0.22800492332171055, "asr_chrf": 0.8922038015648965, "t2t_score": 0.6987626866236131, "s2t_score": 0.5601043624433035 }, { "language_name": "Punjabi", "bcp_47": "pa", "speakers": 203571210, "scores": [ { "model": "openai/gpt-4o-mini", "model_type": "text-to-text", "mt_bleu": 0.31712197840223066, "mt_chrf": 0.46859907170069276, "cls_acc": 0.3, "mlm_chrf": 0.8891660761810072, "t2t_score": 0.5525883826272333 }, { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.3260979917168239, "mt_chrf": 0.48620285493698817, "cls_acc": 0.4, "mlm_chrf": 0.8966325892385384, "t2t_score": 0.5942784813918421 }, { "model": "mistralai/mistral-small-24b-instruct-2501", "model_type": "text-to-text", "mt_bleu": 0.2187115929653566, "mt_chrf": 0.3524175363784819, "cls_acc": 0.3, "mlm_chrf": 0.8850095336403061, "t2t_score": 0.5124756900062627 }, { "model": "google/gemini-2.0-flash-001", "model_type": "text-to-text", "mt_bleu": 0.3778935484806146, "mt_chrf": 0.5344045974435822, "cls_acc": 0.8666666666666667, "mlm_chrf": 0.9084722630859033, "t2t_score": 0.7698478423987174 }, { "model": "elevenlabs/scribe_v1", "model_type": "speech-to-text", "asr_wer": 0.2622994225519276, "asr_chrf": 0.7896064299629604, "s2t_score": 0.525952926257444 } ], "commonvoice_hours": 2.3, "commonvoice_locale": "pa-IN", "population": { "CA": 603106, "GB": 2367400, "IN": 37130520, "KE": 10170, "PK": 163450700, "SG": 9314 }, "language_family": "Indo-European", "mt_bleu": 0.30995627789125646, "mt_chrf": 0.4604060151149363, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.8948201155364387, "asr_wer": 0.2622994225519276, "asr_chrf": 0.7896064299629604, "t2t_score": 0.6072975991060139, "s2t_score": 0.525952926257444 }, { "language_name": "Russian", "bcp_47": "ru", "speakers": 195841151, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.21923866610511508, "mt_chrf": 0.4198761129214811, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.952484813474142, "t2t_score": 0.6685647532429854 } ], "commonvoice_hours": 242.0, "commonvoice_locale": "ru", "population": { "BG": 1602387, "BY": 1137350, "CA": 211087, "CN": 13940, "DE": 4809582, "EE": 688027, "FI": 45131, "GE": 359730, "IL": 954303, "KG": 2147364, "KZ": 13746168, "LT": 2185168, "LV": 714867, "MD": 100935, "MN": 4118, "PL": 6890814, "RU": 133218680, "SJ": 1200, "TJ": 1064840, "TM": 663436, "UA": 20204534, "US": 798334, "UZ": 4279156 }, "language_family": "Indo-European", "mt_bleu": 0.21923866610511508, "mt_chrf": 0.4198761129214811, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.952484813474142, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6685647532429854, "s2t_score": null }, { "language_name": "Swahili", "bcp_47": "sw", "speakers": 171610296, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2687578645492076, "mt_chrf": 0.43597304968281303, "cls_acc": 0.6, "mlm_chrf": 0.9381149118648788, "t2t_score": 0.6580293205158972 } ], "commonvoice_hours": 411.0, "commonvoice_locale": "sw", "population": { "BI": 6408, "CD": 50890000, "KE": 35328414, "MZ": 9330, "SO": 235142, "TZ": 52697520, "UG": 32439750, "YT": 2716, "ZA": 1016 }, "language_family": "Atlantic-Congo", "mt_bleu": 0.2687578645492076, "mt_chrf": 0.43597304968281303, "cls_acc": 0.6, "mlm_chrf": 0.9381149118648788, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6580293205158972, "s2t_score": null }, { "language_name": "Indonesian", "bcp_47": "id", "speakers": 171207687, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2848563065102788, "mt_chrf": 0.45614479099339716, "cls_acc": 0.6, "mlm_chrf": 0.9430041038670292, "t2t_score": 0.6663829649534755 } ], "commonvoice_hours": 33.0, "commonvoice_locale": "id", "population": { "ID": 170896640, "NL": 311047 }, "language_family": "Austronesian", "mt_bleu": 0.2848563065102788, "mt_chrf": 0.45614479099339716, "cls_acc": 0.6, "mlm_chrf": 0.9430041038670292, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6663829649534755, "s2t_score": null }, { "language_name": "German", "bcp_47": "de", "speakers": 136350226, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.31823711841849867, "mt_chrf": 0.4917464754926922, "cls_acc": 0.6666666666666666, "mlm_chrf": 0.9691031216506188, "t2t_score": 0.7091720879366593 } ], "commonvoice_hours": 1359.0, "commonvoice_locale": "de", "population": { "AT": 8593666, "BE": 2578554, "BG": 557352, "BR": 1778414, "CA": 294014, "CH": 6134913, "CZ": 1605375, "DE": 72945327, "DK": 2758623, "FI": 1002901, "FR": 3392410, "GB": 5918499, "GR": 530355, "HU": 1758929, "IT": 998443, "KZ": 1221882, "LI": 39137, "LT": 382404, "LU": 395880, "NA": 23671, "NL": 12269084, "PL": 7273637, "PY": 208559, "RO": 44736, "SI": 883126, "SK": 1196932, "US": 1563403 }, "language_family": "Indo-European", "mt_bleu": 0.31823711841849867, "mt_chrf": 0.4917464754926922, "cls_acc": 0.6666666666666666, "mlm_chrf": 0.9691031216506188, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.7091720879366593, "s2t_score": null }, { "language_name": "Japanese", "bcp_47": "ja", "speakers": 119729026, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2683560704622462, "mt_chrf": 0.4411714629040184, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9391550198474721, "t2t_score": 0.6378866053616079 } ], "commonvoice_hours": 222.0, "commonvoice_locale": "ja", "population": { "BR": 444604, "CA": 52772, "JP": 119231650 }, "language_family": "Japonic", "mt_bleu": 0.2683560704622462, "mt_chrf": 0.4411714629040184, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9391550198474721, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6378866053616079, "s2t_score": null }, { "language_name": "Telugu", "bcp_47": "te", "speakers": 95478480, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.26607890997092576, "mt_chrf": 0.4454927673606575, "cls_acc": 0.36666666666666664, "mlm_chrf": 0.9537042790563578, "t2t_score": 0.5886212376945607 } ], "commonvoice_hours": 0.3, "commonvoice_locale": "te", "population": { "IN": 95478480 }, "language_family": "Dravidian", "mt_bleu": 0.26607890997092576, "mt_chrf": 0.4454927673606575, "cls_acc": 0.36666666666666664, "mlm_chrf": 0.9537042790563578, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5886212376945607, "s2t_score": null }, { "language_name": "Western Panjabi", "bcp_47": "lah", "speakers": 93433552, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 33152, "PK": 93400400 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Marathi", "bcp_47": "mr", "speakers": 92826300, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.22832077978859452, "mt_chrf": 0.42452032963429065, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.9408962186478436, "t2t_score": 0.6662499605384892 } ], "commonvoice_hours": 20.0, "commonvoice_locale": "mr", "population": { "IN": 92826300 }, "language_family": "Indo-European", "mt_bleu": 0.22832077978859452, "mt_chrf": 0.42452032963429065, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.9408962186478436, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6662499605384892, "s2t_score": null }, { "language_name": "Javanese", "bcp_47": "jv", "speakers": 91180665, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.25461973194021953, "mt_chrf": 0.42962098287756895, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9314748203362577, "t2t_score": 0.6425874899601645 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "jv", "population": { "ID": 90788840, "MY": 391825 }, "language_family": "Austronesian", "mt_bleu": 0.25461973194021953, "mt_chrf": 0.42962098287756895, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9314748203362577, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6425874899601645, "s2t_score": null }, { "language_name": "Vietnamese", "bcp_47": "vi", "speakers": 86222962, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.23107984716515417, "mt_chrf": 0.4169594776564998, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9518257555072703, "t2t_score": 0.6118172999434789 } ], "commonvoice_hours": 5.9, "commonvoice_locale": "vi", "population": { "CA": 184701, "CN": 6970, "US": 1130973, "VN": 84900318 }, "language_family": "Austroasiatic", "mt_bleu": 0.23107984716515417, "mt_chrf": 0.4169594776564998, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9518257555072703, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6118172999434789, "s2t_score": null }, { "language_name": "Tamil", "bcp_47": "ta", "speakers": 85616159, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2275590311337094, "mt_chrf": 0.39686916122496285, "cls_acc": 0.43333333333333335, "mlm_chrf": 0.9472514842672666, "t2t_score": 0.5924846596085209 } ], "commonvoice_hours": 234.0, "commonvoice_locale": "ta", "population": { "CA": 184701, "GB": 2104355, "IN": 78239310, "LK": 3433380, "MU": 34484, "MY": 1371388, "RE": 118138, "SG": 130403 }, "language_family": "Dravidian", "mt_bleu": 0.2275590311337094, "mt_chrf": 0.39686916122496285, "cls_acc": 0.43333333333333335, "mlm_chrf": 0.9472514842672666, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5924846596085209, "s2t_score": null }, { "language_name": "Persian", "bcp_47": "fa", "speakers": 84710459, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2516753344674677, "mt_chrf": 0.4448545956789697, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9507199271394501, "t2t_score": 0.6207470631616955 } ], "commonvoice_hours": 370.0, "commonvoice_locale": "fa", "population": { "AE": 189850, "AF": 18321900, "CA": 245012, "IQ": 338192, "IR": 63692475, "OM": 43849, "PK": 1541107, "QA": 268859, "TJ": 69215 }, "language_family": "Indo-European", "mt_bleu": 0.2516753344674677, "mt_chrf": 0.4448545956789697, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9507199271394501, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6207470631616955, "s2t_score": null }, { "language_name": "Wu Chinese", "bcp_47": "wuu", "speakers": 83641200, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 83641200 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Turkish", "bcp_47": "tr", "speakers": 80360704, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.28856187360515456, "mt_chrf": 0.44838344659789414, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.942880312425148, "t2t_score": 0.6415323641187918 } ], "commonvoice_hours": 127.0, "commonvoice_locale": "tr", "population": { "BG": 766359, "CA": 37694, "CY": 291336, "DE": 2003992, "GB": 131522, "GR": 127285, "MK": 74409, "NL": 207365, "RO": 27694, "TR": 76276275, "UA": 184476, "UZ": 232297 }, "language_family": "Turkic", "mt_bleu": 0.28856187360515456, "mt_chrf": 0.44838344659789414, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.942880312425148, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6415323641187918, "s2t_score": null }, { "language_name": "Cantonese", "bcp_47": "yue", "speakers": 79654759, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2429350313522061, "mt_chrf": 0.43687518387422897, "cls_acc": 0.6, "mlm_chrf": 0.908223660437837, "t2t_score": 0.6483662814373553 } ], "commonvoice_hours": 203.0, "commonvoice_locale": "yue", "population": { "CA": 640800, "CN": 72489040, "HK": 6524919 }, "language_family": "Sino-Tibetan", "mt_bleu": 0.2429350313522061, "mt_chrf": 0.43687518387422897, "cls_acc": 0.6, "mlm_chrf": 0.908223660437837, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6483662814373553, "s2t_score": null }, { "language_name": "Korean", "bcp_47": "ko", "speakers": 78357046, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.21969579072372622, "mt_chrf": 0.4134343535369621, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9227146395635537, "t2t_score": 0.6342718865890609 } ], "commonvoice_hours": 1.7, "commonvoice_locale": "ko", "population": { "BR": 44460, "CA": 169623, "CN": 2091030, "JP": 652636, "KP": 22566280, "KR": 51835100, "US": 997917 }, "language_family": "Koreanic", "mt_bleu": 0.21969579072372622, "mt_chrf": 0.4134343535369621, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9227146395635537, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6342718865890609, "s2t_score": null }, { "language_name": "Italian", "bcp_47": "it", "speakers": 70247060, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2774810104440749, "mt_chrf": 0.46396483435604213, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.9708848195292886, "t2t_score": 0.689394329072888 } ], "commonvoice_hours": 362.0, "commonvoice_locale": "it", "population": { "AT": 797350, "AU": 483864, "BR": 592805, "CA": 343016, "CH": 361372, "DE": 5611179, "FR": 1153419, "GB": 131522, "HR": 67644, "IT": 59282565, "MT": 256070, "SI": 3995, "SM": 30466, "US": 1130973, "VA": 820 }, "language_family": "Indo-European", "mt_bleu": 0.2774810104440749, "mt_chrf": 0.46396483435604213, "cls_acc": 0.6333333333333333, "mlm_chrf": 0.9708848195292886, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.689394329072888, "s2t_score": null }, { "language_name": "Filipino", "bcp_47": "fil", "speakers": 67471096, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.3248927726984041, "mt_chrf": 0.4689020729383555, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.954910715229284, "t2t_score": 0.6301598182781021 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "tl", "population": { "CA": 565412, "PH": 65508600, "US": 1397084 }, "language_family": "Austronesian", "mt_bleu": 0.3248927726984041, "mt_chrf": 0.4689020729383555, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.954910715229284, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6301598182781021, "s2t_score": null }, { "language_name": "Egyptian Arabic", "bcp_47": "arz", "speakers": 66639360, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.20127691717583832, "mt_chrf": 0.3878019842631749, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9209179960794297, "t2t_score": 0.6251288823364237 } ], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "EG": 66639360 }, "language_family": "Afro-Asiatic", "mt_bleu": 0.20127691717583832, "mt_chrf": 0.3878019842631749, "cls_acc": 0.5666666666666667, "mlm_chrf": 0.9209179960794297, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6251288823364237, "s2t_score": null }, { "language_name": "Gujarati", "bcp_47": "gu", "speakers": 61721799, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.24812610549809738, "mt_chrf": 0.4318359636701651, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9077297218306815, "t2t_score": 0.6020774507225044 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "gu-IN", "population": { "CA": 135699, "GB": 1907072, "IN": 59674050, "KE": 4978 }, "language_family": "Indo-European", "mt_bleu": 0.24812610549809738, "mt_chrf": 0.4318359636701651, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9077297218306815, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6020774507225044, "s2t_score": null }, { "language_name": "Thai", "bcp_47": "th", "speakers": 55181920, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2267380896222089, "mt_chrf": 0.4196149454731818, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9450374989027414, "t2t_score": 0.6326619259030855 } ], "commonvoice_hours": 172.0, "commonvoice_locale": "th", "population": { "TH": 55181920 }, "language_family": "Tai-Kadai", "mt_bleu": 0.2267380896222089, "mt_chrf": 0.4196149454731818, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9450374989027414, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6326619259030855, "s2t_score": null }, { "language_name": "Pashto", "bcp_47": "ps", "speakers": 53542641, "scores": [], "commonvoice_hours": 79.0, "commonvoice_locale": "ps", "population": { "AE": 289770, "AF": 15756834, "IR": 135877, "PK": 37360160 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kannada", "bcp_47": "kn", "speakers": 49065330, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.25507181761037034, "mt_chrf": 0.4455588394992276, "cls_acc": 0.4, "mlm_chrf": 0.9511289423946643, "t2t_score": 0.5988959272979639 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "kn", "population": { "IN": 49065330 }, "language_family": "Dravidian", "mt_bleu": 0.25507181761037034, "mt_chrf": 0.4455588394992276, "cls_acc": 0.4, "mlm_chrf": 0.9511289423946643, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5988959272979639, "s2t_score": null }, { "language_name": "Nigerian Pidgin", "bcp_47": "pcm", "speakers": 44945880, "scores": [], "commonvoice_hours": 14.0, "commonvoice_locale": "pcm", "population": { "NG": 44945880 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Malayalam", "bcp_47": "ml", "speakers": 43257484, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2011475124105192, "mt_chrf": 0.39404171184956394, "cls_acc": 0.43333333333333335, "mlm_chrf": 0.9231097391098181, "t2t_score": 0.5834949280975718 } ], "commonvoice_hours": 2.8, "commonvoice_locale": "ml", "population": { "AE": 699446, "BH": 49665, "IL": 7981, "IN": 42434880, "MY": 48978, "QA": 6599, "SG": 9935 }, "language_family": "Dravidian", "mt_bleu": 0.2011475124105192, "mt_chrf": 0.39404171184956394, "cls_acc": 0.43333333333333335, "mlm_chrf": 0.9231097391098181, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5834949280975718, "s2t_score": null }, { "language_name": "Odia", "bcp_47": "or", "speakers": 42434880, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2521285657827072, "mt_chrf": 0.4422326291663303, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9217590917135282, "t2t_score": 0.6102194625155084 } ], "commonvoice_hours": 2.8, "commonvoice_locale": "or", "population": { "IN": 42434880 }, "language_family": "Indo-European", "mt_bleu": 0.2521285657827072, "mt_chrf": 0.4422326291663303, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.9217590917135282, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6102194625155084, "s2t_score": null }, { "language_name": "Polish", "bcp_47": "pl", "speakers": 41077399, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.26987204535648013, "mt_chrf": 0.4562492816384855, "cls_acc": 0.6, "mlm_chrf": 0.9584939056009891, "t2t_score": 0.6715810624131583 } ], "commonvoice_hours": 174.0, "commonvoice_locale": "pl", "population": { "CA": 173393, "CZ": 52442, "DE": 232463, "GB": 2630444, "IL": 130132, "PL": 36751008, "RO": 2769, "SK": 50598, "UA": 1054150 }, "language_family": "Indo-European", "mt_bleu": 0.26987204535648013, "mt_chrf": 0.4562492816384855, "cls_acc": 0.6, "mlm_chrf": 0.9584939056009891, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6715810624131583, "s2t_score": null }, { "language_name": "Xiang Chinese", "bcp_47": "hsn", "speakers": 40426580, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 40426580 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hausa", "bcp_47": "ha", "speakers": 40411882, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.14767816277169446, "mt_chrf": 0.3435397334736881, "cls_acc": 0.6, "mlm_chrf": 0.9296807495100402, "t2t_score": 0.6244068276612428 } ], "commonvoice_hours": 4.1, "commonvoice_locale": "ha", "population": { "CM": 38843, "GH": 252326, "NE": 9336684, "NG": 29963920, "SD": 820109 }, "language_family": "Afro-Asiatic", "mt_bleu": 0.14767816277169446, "mt_chrf": 0.3435397334736881, "cls_acc": 0.6, "mlm_chrf": 0.9296807495100402, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6244068276612428, "s2t_score": null }, { "language_name": "Sindhi", "bcp_47": "sd", "speakers": 40329510, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.21679684560539594, "mt_chrf": 0.4130326388570074, "cls_acc": 0.3333333333333333, "mlm_chrf": 0.9140884463880482, "t2t_score": 0.5534848061927963 } ], "commonvoice_hours": 0.4, "commonvoice_locale": "sd", "population": { "IN": 5304360, "PK": 35025150 }, "language_family": "Indo-European", "mt_bleu": 0.21679684560539594, "mt_chrf": 0.4130326388570074, "cls_acc": 0.3333333333333333, "mlm_chrf": 0.9140884463880482, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5534848061927963, "s2t_score": null }, { "language_name": "North Levantine Arabic", "bcp_47": "apc", "speakers": 39031474, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IL": 1474832, "JO": 7141596, "LB": 5469610, "PS": 4191886, "SY": 16488640, "TR": 4264910 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Malay", "bcp_47": "ms", "speakers": 38097307, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.2640387431669489, "mt_chrf": 0.45903065670305865, "cls_acc": 0.6, "mlm_chrf": 0.953241903654886, "t2t_score": 0.6707575201193148 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "ms", "population": { "BN": 455189, "CC": 495, "ID": 12283196, "MY": 24489075, "SG": 869352 }, "language_family": "Austronesian", "mt_bleu": 0.2640387431669489, "mt_chrf": 0.45903065670305865, "cls_acc": 0.6, "mlm_chrf": 0.953241903654886, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6707575201193148, "s2t_score": null }, { "language_name": "Burmese", "bcp_47": "my", "speakers": 36559231, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.18617334539824332, "mt_chrf": 0.37050602802081317, "cls_acc": 0.4, "mlm_chrf": 0.9435884643372262, "t2t_score": 0.5713648307860132 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "my", "population": { "BD": 341567, "MM": 36217664 }, "language_family": "Sino-Tibetan", "mt_bleu": 0.18617334539824332, "mt_chrf": 0.37050602802081317, "cls_acc": 0.4, "mlm_chrf": 0.9435884643372262, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5713648307860132, "s2t_score": null }, { "language_name": "Amharic", "bcp_47": "am", "speakers": 35728475, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.15002522598066087, "mt_chrf": 0.3344555209113584, "cls_acc": 0.36666666666666664, "mlm_chrf": 0.9209607335412187, "t2t_score": 0.540694307039748 } ], "commonvoice_hours": 1.8, "commonvoice_locale": "am", "population": { "ET": 35677290, "IL": 51185 }, "language_family": "Afro-Asiatic", "mt_bleu": 0.15002522598066087, "mt_chrf": 0.3344555209113584, "cls_acc": 0.36666666666666664, "mlm_chrf": 0.9209607335412187, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.540694307039748, "s2t_score": null }, { "language_name": "Algerian Arabic", "bcp_47": "arq", "speakers": 35667507, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DZ": 35667507 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Oromo", "bcp_47": "om", "speakers": 34897121, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.06509147151730071, "mt_chrf": 0.22674886804446034, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.935213305660654, "t2t_score": 0.542876280123927 } ], "commonvoice_hours": 0.0, "commonvoice_locale": "om", "population": { "ET": 34596160, "KE": 251581, "SO": 49380 }, "language_family": "Afro-Asiatic", "mt_bleu": 0.06509147151730071, "mt_chrf": 0.22674886804446034, "cls_acc": 0.4666666666666667, "mlm_chrf": 0.935213305660654, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.542876280123927, "s2t_score": null }, { "language_name": "Bhojpuri", "bcp_47": "bho", "speakers": 32934797, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.24092898437545654, "mt_chrf": 0.41894143077328727, "cls_acc": 0.3333333333333333, "mlm_chrf": 0.9323077688040071, "t2t_score": 0.5615275109702093 } ], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 30500070, "MU": 372430, "NP": 2062297 }, "language_family": "Indo-European", "mt_bleu": 0.24092898437545654, "mt_chrf": 0.41894143077328727, "cls_acc": 0.3333333333333333, "mlm_chrf": 0.9323077688040071, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.5615275109702093, "s2t_score": null }, { "language_name": "Uzbek", "bcp_47": "uz", "speakers": 32792780, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.21766825893077735, "mt_chrf": 0.41950879947755915, "cls_acc": 0.5, "mlm_chrf": 0.9467806955511296, "t2t_score": 0.6220964983428963 } ], "commonvoice_hours": 100.0, "commonvoice_locale": "uz", "population": { "AF": 1722259, "CN": 5576, "TM": 497577, "TR": 1968, "UZ": 30565400 }, "language_family": "Turkic", "mt_bleu": 0.21766825893077735, "mt_chrf": 0.41950879947755915, "cls_acc": 0.5, "mlm_chrf": 0.9467806955511296, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.6220964983428963, "s2t_score": null }, { "language_name": "Azerbaijani", "bcp_47": "az", "speakers": 32446682, "scores": [ { "model": "meta-llama/llama-3.3-70b-instruct", "model_type": "text-to-text", "mt_bleu": 0.1836488163977562, "mt_chrf": 0.37916693488563025, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9328142884587273, "t2t_score": 0.615104852225897 } ], "commonvoice_hours": 0.5, "commonvoice_locale": "az", "population": { "AM": 0, "AZ": 10093536, "IQ": 699709, "IR": 20381592, "RU": 131801, "TR": 1140044 }, "language_family": "Turkic", "mt_bleu": 0.1836488163977562, "mt_chrf": 0.37916693488563025, "cls_acc": 0.5333333333333333, "mlm_chrf": 0.9328142884587273, "asr_wer": null, "asr_chrf": null, "t2t_score": 0.615104852225897, "s2t_score": null }, { "language_name": "Hakka Chinese", "bcp_47": "hak", "speakers": 32062460, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 32062460 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sundanese", "bcp_47": "su", "speakers": 32043120, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 32043120 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dutch", "bcp_47": "nl", "speakers": 31765645, "scores": [], "commonvoice_hours": 114.0, "commonvoice_locale": "nl", "population": { "AW": 115845, "BE": 6446385, "BQ": 1600, "CA": 56541, "CW": 12108, "DE": 7214373, "FR": 88203, "NL": 17280400, "SR": 548612, "SX": 1578 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Moroccan Arabic", "bcp_47": "ary", "speakers": 30938679, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MA": 30938679 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ukrainian", "bcp_47": "uk", "speakers": 29348975, "scores": [], "commonvoice_hours": 98.0, "commonvoice_locale": "uk", "population": { "CA": 75388, "MD": 471030, "PL": 149301, "RS": 0, "SK": 103371, "UA": 28549885 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yoruba", "bcp_47": "yo", "speakers": 28685568, "scores": [], "commonvoice_hours": 6.0, "commonvoice_locale": "yo", "population": { "BJ": 861928, "NG": 27823640 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Saraiki", "bcp_47": "skr", "speakers": 28020120, "scores": [], "commonvoice_hours": 4.3, "commonvoice_locale": "skr", "population": { "PK": 28020120 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Igbo", "bcp_47": "ig", "speakers": 27823640, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ig", "population": { "NG": 27823640 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Min Nan Chinese", "bcp_47": "nan", "speakers": 26486380, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 26486380 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Cebuano", "bcp_47": "ceb", "speakers": 26203440, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 26203440 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Awadhi", "bcp_47": "awa", "speakers": 25862924, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 25195710, "NP": 667214 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Malagasy", "bcp_47": "mg", "speakers": 24260130, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "mg", "population": { "MG": 24260130 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gan Chinese", "bcp_47": "gan", "speakers": 23698340, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 23698340 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Romanian", "bcp_47": "ro", "speakers": 22187408, "scores": [], "commonvoice_hours": 21.0, "commonvoice_locale": "ro", "population": { "CA": 101774, "HU": 96741, "IL": 320993, "MD": 2119635, "RO": 19172610, "RS": 147256, "UA": 228399 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bavarian", "bcp_47": "bar", "speakers": 22043627, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AT": 8416478, "DE": 13627149 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nepali", "bcp_47": "ne", "speakers": 20903374, "scores": [], "commonvoice_hours": 1.3, "commonvoice_locale": "ne-NP", "population": { "BT": 132994, "IN": 7426104, "NP": 13344276 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Maithili", "bcp_47": "mai", "speakers": 19249149, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "mai", "population": { "IN": 15913080, "NP": 3336069 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Assamese", "bcp_47": "as", "speakers": 17239170, "scores": [], "commonvoice_hours": 2.8, "commonvoice_locale": "as", "population": { "IN": 17239170 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nyanja", "bcp_47": "ny", "speakers": 17026781, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ny", "population": { "MW": 13353858, "MZ": 782553, "ZM": 2613990, "ZW": 276380 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Somali", "bcp_47": "so", "speakers": 16911645, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "so", "population": { "CA": 49002, "DJ": 377940, "ET": 6486780, "GB": 131522, "KE": 695863, "SO": 9170538 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Madurese", "bcp_47": "mad", "speakers": 16822638, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 16822638 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northeastern Thai", "bcp_47": "tts", "speakers": 16554576, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TH": 16554576 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rangpuri", "bcp_47": "rkt", "speakers": 16274502, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BD": 10572315, "IN": 5702187 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Magahi", "bcp_47": "mag", "speakers": 15913080, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 15913080 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Haryanvi", "bcp_47": "bgc", "speakers": 15913080, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 15913080 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Marwari", "bcp_47": "mwr", "speakers": 15913080, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 15913080 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Serbian", "bcp_47": "sr", "speakers": 15602410, "scores": [], "commonvoice_hours": 7.5, "commonvoice_locale": "sr", "population": { "BA": 767118, "CA": 64080, "ME": 640352, "RO": 25563, "RS": 13884096, "RU": 4960, "TR": 22965, "XK": 193276 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sinhala", "bcp_47": "si", "speakers": 15564656, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "si", "population": { "LK": 15564656 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Khmer", "bcp_47": "km", "speakers": 15065030, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "km", "population": { "KH": 15065030 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chhattisgarhi", "bcp_47": "hne", "speakers": 14586990, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 14586990 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nigerian Fulfulde", "bcp_47": "fuv", "speakers": 14339876, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 14339876 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zulu", "bcp_47": "zu", "speakers": 13973830, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "zu", "population": { "LS": 275706, "MW": 69949, "MZ": 1806, "SZ": 75105, "ZA": 13551264 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kazakh", "bcp_47": "kk", "speakers": 13637392, "scores": [], "commonvoice_hours": 2.1, "commonvoice_locale": "kk", "population": { "AF": 2015, "CN": 1184917, "IR": 2972, "KZ": 12218816, "MN": 228098, "TR": 574 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Deccan", "bcp_47": "dcc", "speakers": 13128291, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 13128291 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Czech", "bcp_47": "cs", "speakers": 13045532, "scores": [], "commonvoice_hours": 74.0, "commonvoice_locale": "cs", "population": { "CZ": 10488450, "SK": 2557082 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Swedish", "bcp_47": "sv", "speakers": 12932871, "scores": [], "commonvoice_hours": 47.0, "commonvoice_locale": "sv-SE", "population": { "AX": 25938, "DK": 763023, "FI": 2451535, "SE": 9692375 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hungarian", "bcp_47": "hu", "speakers": 12443430, "scores": [], "commonvoice_hours": 92.0, "commonvoice_locale": "hu", "population": { "AT": 23035, "CA": 49002, "HU": 9771830, "IL": 86755, "RO": 1405991, "RS": 336584, "SI": 9252, "SK": 598466, "UA": 162515 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Greek", "bcp_47": "el", "speakers": 12292242, "scores": [], "commonvoice_hours": 20.0, "commonvoice_locale": "el", "population": { "AL": 58417, "CA": 124391, "CY": 1203346, "DE": 304607, "EG": 63516, "GR": 10501029, "IT": 21841, "RO": 4048, "TR": 4019, "UA": 7028 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Shona", "bcp_47": "sn", "speakers": 11782503, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ZW": 11782503 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Low German", "bcp_47": "nds", "speakers": 11520008, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 9619164, "NL": 1900844 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Akan", "bcp_47": "ak", "speakers": 11442678, "scores": [], "commonvoice_hours": 0.1, "commonvoice_locale": "tw", "population": { "GH": 11442678 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Quechua", "bcp_47": "qu", "speakers": 11385851, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BO": 3724768, "EC": 2873833, "PE": 4787250 }, "language_family": "Quechuan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Kurdish", "bcp_47": "ckb", "speakers": 11086549, "scores": [], "commonvoice_hours": 135.0, "commonvoice_locale": "ckb", "population": { "IQ": 7774540, "IR": 3312009 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kinyarwanda", "bcp_47": "rw", "speakers": 11083625, "scores": [], "commonvoice_hours": 2002.0, "commonvoice_locale": "rw", "population": { "CD": 386764, "RW": 9788548, "UG": 908313 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Wolof", "bcp_47": "wo", "speakers": 11025494, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "wo", "population": { "MR": 10014, "SN": 11015480 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tunisian Arabic", "bcp_47": "aeb", "speakers": 10549080, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TN": 10549080 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Iloko", "bcp_47": "ilo", "speakers": 10481376, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 10481376 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Xhosa", "bcp_47": "xh", "speakers": 10182944, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "xh", "population": { "LS": 19496, "ZA": 10163448 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tigrinya", "bcp_47": "ti", "speakers": 10145911, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ti", "population": { "ER": 3648720, "ET": 6486780, "IL": 10411 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Belarusian", "bcp_47": "be", "speakers": 10064517, "scores": [], "commonvoice_hours": 1804.0, "commonvoice_locale": "be", "population": { "BY": 9477920, "PL": 222037, "UA": 364560 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Luba-Lulua", "bcp_47": "lua", "speakers": 9770880, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CD": 9770880 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tajik", "bcp_47": "tg", "speakers": 9644223, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "tg", "population": { "PK": 770553, "TJ": 8873670 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Umbundu", "bcp_47": "umb", "speakers": 9431467, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AO": 9431467 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bambara", "bcp_47": "bm", "speakers": 9385632, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "bm", "population": { "ML": 9385632 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Afrikaans", "bcp_47": "af", "speakers": 9318845, "scores": [], "commonvoice_hours": 0.5, "commonvoice_locale": "af", "population": { "BW": 6025, "NA": 1972552, "ZA": 7340268 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hiligaynon", "bcp_47": "hil", "speakers": 9171204, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "hil", "population": { "PH": 9171204 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kikuyu", "bcp_47": "ki", "speakers": 9099743, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ki", "population": { "KE": 9099743 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Haitian Creole", "bcp_47": "ht", "speakers": 8964918, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ht", "population": { "HT": 8964918 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Catalan", "bcp_47": "ca", "speakers": 8679139, "scores": [], "commonvoice_hours": 2842.0, "commonvoice_locale": "ca", "population": { "AD": 39270, "ES": 8502686, "FR": 115342, "IT": 21841 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hebrew", "bcp_47": "he", "speakers": 8675480, "scores": [], "commonvoice_hours": 1.1, "commonvoice_locale": "he", "population": { "IL": 8675480 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sichuan Yi", "bcp_47": "ii", "speakers": 8364120, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 8364120 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mossi", "bcp_47": "mos", "speakers": 8334160, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "mos", "population": { "BF": 8334160 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Baluchi", "bcp_47": "bal", "speakers": 8227887, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "bal", "population": { "AE": 229818, "IR": 1698466, "OM": 228577, "PK": 6071026 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sylheti", "bcp_47": "syl", "speakers": 8132550, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BD": 8132550 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kimbundu", "bcp_47": "kmb", "speakers": 8130575, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AO": 8130575 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Uyghur", "bcp_47": "ug", "speakers": 8052967, "scores": [], "commonvoice_hours": 364.0, "commonvoice_locale": "ug", "population": { "AF": 3005, "CN": 7667110, "KZ": 381838, "MN": 1014 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Minangkabau", "bcp_47": "min", "speakers": 8010780, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 8010780 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Swiss German", "bcp_47": "gsw", "speakers": 7956952, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "gsw", "population": { "CH": 5462594, "DE": 1843673, "FR": 617419, "LI": 33266 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bulgarian", "bcp_47": "bg", "speakers": 7878315, "scores": [], "commonvoice_hours": 16.0, "commonvoice_locale": "bg", "population": { "BG": 6966900, "GR": 28639, "MD": 316263, "RO": 6817, "TR": 344474, "UA": 215222 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Standard Moroccan Tamazight", "bcp_47": "zgh", "speakers": 7823574, "scores": [], "commonvoice_hours": 1.3, "commonvoice_locale": "zgh", "population": { "MA": 7823574 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Fula", "bcp_47": "ff", "speakers": 7788904, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ff", "population": { "BF": 0, "CM": 998820, "GH": 0, "GM": 0, "GN": 3257124, "GW": 4, "LR": 0, "MR": 228312, "NE": 0, "NG": 0, "SL": 0, "SN": 3304644 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bosnian", "bcp_47": "bs", "speakers": 7594468, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "bs", "population": { "BA": 7594468 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rundi", "bcp_47": "rn", "speakers": 7475454, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "rn", "population": { "BI": 7475454 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kanauji", "bcp_47": "bjj", "speakers": 7426104, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 7426104 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Santali", "bcp_47": "sat", "speakers": 7293495, "scores": [], "commonvoice_hours": 0.5, "commonvoice_locale": "sat", "population": { "IN": 7293495 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Danish", "bcp_47": "da", "speakers": 7072056, "scores": [], "commonvoice_hours": 13.0, "commonvoice_locale": "da", "population": { "DE": 1603194, "DK": 5458551, "GL": 8066, "IS": 2245 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Turkmen", "bcp_47": "tk", "speakers": 6870838, "scores": [], "commonvoice_hours": 2.8, "commonvoice_locale": "tk", "population": { "AF": 622945, "IR": 2377852, "TM": 3870041 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kurdish", "bcp_47": "ku", "speakers": 6866757, "scores": [], "commonvoice_hours": 69.0, "commonvoice_locale": "kmr", "population": { "AM": 99704, "AZ": 24494, "DE": 529054, "GE": 35573, "LB": 92983, "SY": 1551872, "TM": 22115, "TR": 4510962 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Croatian", "bcp_47": "hr", "speakers": 6813164, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "hr", "population": { "AT": 106313, "BA": 460271, "CA": 45233, "DE": 633262, "HR": 4185472, "HU": 31270, "IT": 3495, "RS": 65213, "SI": 1282635 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Albanian", "bcp_47": "sq", "speakers": 6791906, "scores": [], "commonvoice_hours": 8.8, "commonvoice_locale": "sq", "population": { "AL": 3074580, "GR": 9971, "ME": 48179, "MK": 531492, "RS": 1332312, "TR": 17224, "XK": 1778148 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Slovak", "bcp_47": "sk", "speakers": 6680269, "scores": [], "commonvoice_hours": 45.0, "commonvoice_locale": "sk", "population": { "CZ": 1712400, "HU": 11726, "RS": 59603, "SK": 4896540 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dyula", "bcp_47": "dyu", "speakers": 6667328, "scores": [], "commonvoice_hours": 0.4, "commonvoice_locale": "dyu", "population": { "BF": 6667328 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Thai", "bcp_47": "nod", "speakers": 6621830, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TH": 6621830 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mongolian", "bcp_47": "mn", "speakers": 6572846, "scores": [], "commonvoice_hours": 46.0, "commonvoice_locale": "mn", "population": { "CN": 3624452, "MN": 2946268, "RU": 2126 }, "language_family": "Mongolic-Khitan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Sotho", "bcp_47": "st", "speakers": 6390567, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "st", "population": { "LS": 1929943, "ZA": 4460624 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Krio", "bcp_47": "kri", "speakers": 6293684, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SL": 6293684 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tachelhit", "bcp_47": "shi", "speakers": 6187736, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "shi", "population": { "MA": 6187736 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tswana", "bcp_47": "tn", "speakers": 6113428, "scores": [], "commonvoice_hours": 4.2, "commonvoice_locale": "tn", "population": { "BW": 1436683, "NA": 14728, "ZA": 4630015, "ZW": 32002 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mewati", "bcp_47": "wtm", "speakers": 6100014, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 6100014 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Luyia", "bcp_47": "luy", "speakers": 5888069, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 5888069 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Guarani", "bcp_47": "gn", "speakers": 5827107, "scores": [], "commonvoice_hours": 3.7, "commonvoice_locale": "gn", "population": { "AR": 21375, "BO": 52380, "PY": 5753352 }, "language_family": "Tupian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Finnish", "bcp_47": "fi", "speakers": 5736842, "scores": [], "commonvoice_hours": 15.0, "commonvoice_locale": "fi", "population": { "EE": 258010, "FI": 5237370, "RU": 17007, "SE": 224455 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ganda", "bcp_47": "lg", "speakers": 5622890, "scores": [], "commonvoice_hours": 437.0, "commonvoice_locale": "lg", "population": { "UG": 5622890 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Betawi", "bcp_47": "bew", "speakers": 5607546, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "bew", "population": { "ID": 5607546 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kashmiri", "bcp_47": "ks", "speakers": 5598085, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ks", "population": { "IN": 5436969, "PK": 161116 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Thai", "bcp_47": "sou", "speakers": 5518192, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TH": 5518192 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Norwegian Bokmål", "bcp_47": "nb", "speakers": 5468932, "scores": [], "commonvoice_hours": 0.1, "commonvoice_locale": "nb-NO", "population": { "NO": 5467440, "SJ": 1492 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Norwegian", "bcp_47": "no", "speakers": 5467440, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NO": 5467440 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bemba", "bcp_47": "bem", "speakers": 5402246, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ZM": 5402246 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Armenian", "bcp_47": "hy", "speakers": 5317273, "scores": [], "commonvoice_hours": 31.0, "commonvoice_locale": "hy-AM", "population": { "AM": 2960894, "CY": 2787, "GE": 279790, "IR": 203816, "LB": 284420, "RU": 1190465, "SY": 349171, "TR": 45930 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Sotho", "bcp_47": "nso", "speakers": 5307578, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "nso", "population": { "ZA": 5307578 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Luo (Kenya and Tanzania)", "bcp_47": "luo", "speakers": 5245734, "scores": [], "commonvoice_hours": 30.0, "commonvoice_locale": "luo", "population": { "KE": 5245734 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tok Pisin", "bcp_47": "tpi", "speakers": 5154217, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PG": 5154217 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lao", "bcp_47": "lo", "speakers": 5138706, "scores": [], "commonvoice_hours": 0.2, "commonvoice_locale": "lo", "population": { "LA": 5138706 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sukuma", "bcp_47": "suk", "speakers": 5094094, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 5094094 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Konkani", "bcp_47": "kok", "speakers": 4906533, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "knn", "population": { "IN": 4906533 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tsonga", "bcp_47": "ts", "speakers": 4880932, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ts", "population": { "MZ": 2377758, "SZ": 18776, "ZA": 2484398 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Main-Franconian", "bcp_47": "vmf", "speakers": 4809582, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 4809582 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Balinese", "bcp_47": "ban", "speakers": 4806468, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 4806468 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ewe", "bcp_47": "ee", "speakers": 4690857, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ee", "population": { "GH": 3227422, "TG": 1463435 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zhuang", "bcp_47": "za", "speakers": 4321462, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 4321462 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Buginese", "bcp_47": "bug", "speakers": 4298211, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 4272416, "MY": 25795 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mazanderani", "bcp_47": "mzn", "speakers": 4246165, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 4246165 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Goan Konkani", "bcp_47": "gom", "speakers": 4243488, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "gom", "population": { "IN": 4243488 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kamba", "bcp_47": "kam", "speakers": 4068120, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "kam", "population": { "KE": 4068120 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kalenjin", "bcp_47": "kln", "speakers": 4068120, "scores": [], "commonvoice_hours": 43.0, "commonvoice_locale": "kln", "population": { "KE": 4068120 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Banjar", "bcp_47": "bjn", "speakers": 4010288, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 4005390, "MY": 4898 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Hindko", "bcp_47": "hno", "speakers": 3969517, "scores": [], "commonvoice_hours": 11.0, "commonvoice_locale": "hno", "population": { "PK": 3969517 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Makhuwa", "bcp_47": "vmw", "speakers": 3912766, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "vmw", "population": { "MZ": 3912766 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gilaki", "bcp_47": "glk", "speakers": 3906472, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 3906472 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lombard", "bcp_47": "lmo", "speakers": 3901518, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CH": 344564, "IT": 3556954 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zarma", "bcp_47": "dje", "speakers": 3871308, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NE": 3871308 }, "language_family": "Songhay", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ndau", "bcp_47": "ndc", "speakers": 3867046, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MZ": 2979722, "ZW": 887324 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sidamo", "bcp_47": "sid", "speakers": 3783955, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ET": 3783955 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Achinese", "bcp_47": "ace", "speakers": 3738364, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ace", "population": { "ID": 3738364 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Shekhawati", "bcp_47": "swv", "speakers": 3713052, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 3713052 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Riffian", "bcp_47": "rif", "speakers": 3692411, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "rif", "population": { "MA": 3485046, "NL": 207365 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Shan", "bcp_47": "shn", "speakers": 3687984, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "shn", "population": { "MM": 3621766, "TH": 66218 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lambadi", "bcp_47": "lmn", "speakers": 3580443, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 3580443 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Garhwali", "bcp_47": "gbm", "speakers": 3580443, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 3580443 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Georgian", "bcp_47": "ka", "speakers": 3543646, "scores": [], "commonvoice_hours": 158.0, "commonvoice_locale": "ka", "population": { "GE": 3437420, "IR": 60296, "TR": 45930 }, "language_family": "Kartvelian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Galician", "bcp_47": "gl", "speakers": 3515530, "scores": [], "commonvoice_hours": 110.0, "commonvoice_locale": "gl", "population": { "ES": 3501106, "PT": 14424 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lingala", "bcp_47": "ln", "speakers": 3514491, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ln", "population": { "AO": 217899, "CD": 3155180, "CF": 14378, "CG": 127034 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mandingo", "bcp_47": "man", "speakers": 3511762, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GM": 630460, "GN": 2881302 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Atlas Tamazight", "bcp_47": "tzm", "speakers": 3485047, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MA": 3485047 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pattani Malay", "bcp_47": "mfa", "speakers": 3448870, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TH": 3448870 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tiv", "bcp_47": "tiv", "speakers": 3424448, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 3424448 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kabyle", "bcp_47": "kab", "speakers": 3351886, "scores": [], "commonvoice_hours": 571.0, "commonvoice_locale": "kab", "population": { "DZ": 3351886 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kyrgyz", "bcp_47": "ky", "speakers": 3338267, "scores": [], "commonvoice_hours": 39.0, "commonvoice_locale": "ky", "population": { "CN": 473967, "KG": 2863152, "TR": 1148 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bikol", "bcp_47": "bik", "speakers": 3275430, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 3275430 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Fon", "bcp_47": "fon", "speakers": 3216150, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BJ": 3216150 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gondi", "bcp_47": "gon", "speakers": 3182616, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 3182616 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Waray", "bcp_47": "war", "speakers": 3166927, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 678, "PH": 3166249 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Kurdish", "bcp_47": "sdh", "speakers": 3142162, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "sdh", "population": { "IR": 3142162 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Brahui", "bcp_47": "brh", "speakers": 3035513, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PK": 3035513 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Baoulé", "bcp_47": "bci", "speakers": 3022921, "scores": [], "commonvoice_hours": 2.0, "commonvoice_locale": "bci", "population": { "CI": 3022921 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tibetan", "bcp_47": "bo", "speakers": 3006697, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "bo", "population": { "CN": 2788040, "IN": 145870, "NP": 72787 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ibibio", "bcp_47": "ibb", "speakers": 2996392, "scores": [], "commonvoice_hours": 2.6, "commonvoice_locale": "ibb", "population": { "NG": 2996392 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Efik", "bcp_47": "efi", "speakers": 2996392, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 2996392 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sango", "bcp_47": "sg", "speakers": 2935521, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CF": 2935521 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kumaoni", "bcp_47": "kfy", "speakers": 2917398, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 2917398 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Aymara", "bcp_47": "ay", "speakers": 2838620, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BO": 2327980, "PE": 510640 }, "language_family": "Aymaran", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nyankole", "bcp_47": "nyn", "speakers": 2724939, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "nyn", "population": { "UG": 2724939 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Jamaican Creole English", "bcp_47": "jam", "speakers": 2668142, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "JM": 2668142 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dogri", "bcp_47": "doi", "speakers": 2652180, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 2652180 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gusii", "bcp_47": "guz", "speakers": 2622867, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 2622867 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sasak", "bcp_47": "sas", "speakers": 2590152, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 2590152 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kurukh", "bcp_47": "kru", "speakers": 2519571, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 2519571 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pampanga", "bcp_47": "pam", "speakers": 2511163, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 2511163 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "West Albay Bikol", "bcp_47": "fbl", "speakers": 2511163, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 2511163 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lithuanian", "bcp_47": "lt", "speakers": 2488617, "scores": [], "commonvoice_hours": 25.0, "commonvoice_locale": "lt", "population": { "GB": 131522, "LT": 2349056, "PL": 8039 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Beja", "bcp_47": "bej", "speakers": 2460326, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SD": 2460326 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Batak Toba", "bcp_47": "bbc", "speakers": 2456639, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 2456639 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sadri", "bcp_47": "sck", "speakers": 2386962, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 2386962 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Waddar", "bcp_47": "wbq", "speakers": 2386962, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 2386962 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Luba-Katanga", "bcp_47": "lu", "speakers": 2340940, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CD": 2340940 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chiga", "bcp_47": "cgg", "speakers": 2335662, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UG": 2335662 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Soga", "bcp_47": "xog", "speakers": 2292409, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UG": 2292409 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Swati", "bcp_47": "ss", "speakers": 2212379, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ss", "population": { "LS": 47264, "SZ": 640598, "ZA": 1524517 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hazaragi", "bcp_47": "haz", "speakers": 2161984, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AF": 2161984 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Meru", "bcp_47": "mer", "speakers": 2141116, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 2141116 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kangri", "bcp_47": "xnr", "speakers": 2121744, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 2121744 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Afar", "bcp_47": "aa", "speakers": 2119663, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "aa", "population": { "DJ": 387158, "ER": 218923, "ET": 1513582 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Teso", "bcp_47": "teo", "speakers": 2082973, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 396106, "UG": 1686867 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lomwe", "bcp_47": "ngl", "speakers": 2046678, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MZ": 2046678 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Occitan", "bcp_47": "oc", "speakers": 2040398, "scores": [], "commonvoice_hours": 1.8, "commonvoice_locale": "oc", "population": { "ES": 4952, "FR": 2035446 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Balochi", "bcp_47": "bgn", "speakers": 2037382, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AF": 230856, "IR": 475570, "PK": 1330956 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Luri", "bcp_47": "lrc", "speakers": 2020512, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IQ": 237123, "IR": 1783389 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Wagdi", "bcp_47": "wbr", "speakers": 1989135, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1989135 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tulu", "bcp_47": "tcy", "speakers": 1989135, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1989135 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Khandesi", "bcp_47": "khn", "speakers": 1989135, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1989135 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tatar", "bcp_47": "tt", "speakers": 1984108, "scores": [], "commonvoice_hours": 32.0, "commonvoice_locale": "tt", "population": { "RU": 1984108 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Slovenian", "bcp_47": "sl", "speakers": 1973181, "scores": [], "commonvoice_hours": 17.0, "commonvoice_locale": "sl", "population": { "AT": 32780, "HU": 4984, "IT": 106085, "SI": 1829332 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Makasar", "bcp_47": "mak", "speakers": 1949290, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 1949290 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Wolaytta", "bcp_47": "wal", "speakers": 1946034, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ET": 1946034 }, "language_family": "Ta-Ne-Omotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nyamwezi", "bcp_47": "nym", "speakers": 1932242, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 1932242 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bodo", "bcp_47": "brx", "speakers": 1856526, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1856526 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lampung Api", "bcp_47": "ljp", "speakers": 1842479, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 1842479 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chuvash", "bcp_47": "cv", "speakers": 1842386, "scores": [], "commonvoice_hours": 27.0, "commonvoice_locale": "cv", "population": { "RU": 1842386 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bashkir", "bcp_47": "ba", "speakers": 1842386, "scores": [], "commonvoice_hours": 259.0, "commonvoice_locale": "ba", "population": { "RU": 1842386 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rohingya", "bcp_47": "rhg", "speakers": 1824082, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BD": 862050, "MM": 962032 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mende", "bcp_47": "men", "speakers": 1813083, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "LR": 24352, "SL": 1788731 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tumbuka", "bcp_47": "tum", "speakers": 1780514, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MW": 1780514 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tamashek", "bcp_47": "tmh", "speakers": 1776965, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 410621, "NE": 1366344 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "North Ndebele", "bcp_47": "nd", "speakers": 1745556, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "nd", "population": { "ZW": 1745556 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Masai", "bcp_47": "mas", "speakers": 1734738, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 856446, "TZ": 878292 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Serer", "bcp_47": "srr", "speakers": 1731004, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 1731004 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nimadi", "bcp_47": "noe", "speakers": 1723917, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1723917 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Timne", "bcp_47": "tem", "speakers": 1722482, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SL": 1722482 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Scots", "bcp_47": "sco", "speakers": 1644028, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "sco", "population": { "GB": 1644028 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lango (Uganda)", "bcp_47": "laj", "speakers": 1643614, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UG": 1643614 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Domari", "bcp_47": "rmt", "speakers": 1613543, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 1613543 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Macedonian", "bcp_47": "mk", "speakers": 1608565, "scores": [], "commonvoice_hours": 18.0, "commonvoice_locale": "mk", "population": { "AL": 14451, "GR": 169714, "MK": 1424400 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Acoli", "bcp_47": "ach", "speakers": 1600361, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UG": 1600361 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central-Eastern Niger Fulfulde", "bcp_47": "fuq", "speakers": 1594068, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NE": 1594068 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bhili", "bcp_47": "bhb", "speakers": 1591308, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1591308 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pangasinan", "bcp_47": "pag", "speakers": 1528534, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 1528534 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kongo", "bcp_47": "kg", "speakers": 1526700, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CD": 1526700 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bini", "bcp_47": "bin", "speakers": 1519599, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 1519599 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Maasina Fulfulde", "bcp_47": "ffm", "speakers": 1505612, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 1505612 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Manipuri", "bcp_47": "mni", "speakers": 1476591, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "mni", "population": { "BD": 17892, "IN": 1458699 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Abron", "bcp_47": "abr", "speakers": 1467010, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GH": 1467010 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Makonde", "bcp_47": "kde", "speakers": 1463820, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 1463820 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gheg Albanian", "bcp_47": "aln", "speakers": 1430250, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "aln", "population": { "XK": 1430250 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Venda", "bcp_47": "ve", "speakers": 1391759, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ve", "population": { "ZA": 1298663, "ZW": 93096 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sena", "bcp_47": "seh", "speakers": 1384517, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MZ": 1384517 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Venetian", "bcp_47": "vec", "speakers": 1380829, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "vec", "population": { "BR": 508118, "HR": 29594, "IT": 811235, "MX": 2444, "SI": 29438 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Susu", "bcp_47": "sus", "speakers": 1378014, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GN": 1378014 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Norwegian Nynorsk", "bcp_47": "nn", "speakers": 1366860, "scores": [], "commonvoice_hours": 1.5, "commonvoice_locale": "nn-NO", "population": { "NO": 1366860 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Makhuwa-Meetto", "bcp_47": "mgh", "speakers": 1354419, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MZ": 1354419 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rajasthani", "bcp_47": "raj", "speakers": 1326090, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1326090 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ho", "bcp_47": "hoc", "speakers": 1312829, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1312829 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Maguindanaon", "bcp_47": "mdh", "speakers": 1310172, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 1310172 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mewari", "bcp_47": "mtr", "speakers": 1286307, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1286307 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bulu", "bcp_47": "bum", "speakers": 1276270, "scores": [], "commonvoice_hours": 9.5, "commonvoice_locale": "bum", "population": { "CM": 1276270 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Masaaba", "bcp_47": "myx", "speakers": 1254337, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UG": 1254337 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mundari", "bcp_47": "unr", "speakers": 1252287, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1246525, "NP": 5762 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Morisyen", "bcp_47": "mfe", "speakers": 1241433, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MU": 1241433 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Irish", "bcp_47": "ga", "speakers": 1237487, "scores": [], "commonvoice_hours": 5.9, "commonvoice_locale": "ga-IE", "population": { "GB": 98642, "IE": 1138845 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Fur", "bcp_47": "fvr", "speakers": 1230163, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SD": 1230163 }, "language_family": "Furan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rejang", "bcp_47": "rej", "speakers": 1228320, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 1228320 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bhilali", "bcp_47": "bhi", "speakers": 1220003, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1220003 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tausug", "bcp_47": "tsg", "speakers": 1200991, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 1200991 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kʼicheʼ", "bcp_47": "quc", "speakers": 1200731, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "quc", "population": { "GT": 1200731 }, "language_family": "Mayan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bakhtiari", "bcp_47": "bqi", "speakers": 1188926, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 1188926 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kpelle", "bcp_47": "kpe", "speakers": 1186303, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GN": 476041, "LR": 710262 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Cebaara Senoufo", "bcp_47": "sef", "speakers": 1181687, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CI": 1181687 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Khmer", "bcp_47": "kxm", "speakers": 1172616, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TH": 1172616 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "West Flemish", "bcp_47": "vls", "speakers": 1172070, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BE": 1172070 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Soninke", "bcp_47": "snk", "speakers": 1153651, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "snk", "population": { "ML": 1153651 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zaza", "bcp_47": "zza", "speakers": 1148245, "scores": [], "commonvoice_hours": 1.8, "commonvoice_locale": "zza", "population": { "TR": 1148245 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Latvian", "bcp_47": "lv", "speakers": 1147550, "scores": [], "commonvoice_hours": 260.0, "commonvoice_locale": "lv", "population": { "LV": 1147550 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dan", "bcp_47": "dnj", "speakers": 1099244, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CI": 1099244 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gorontalo", "bcp_47": "gor", "speakers": 1094807, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 1094807 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tigre", "bcp_47": "tig", "speakers": 1094616, "scores": [], "commonvoice_hours": 3.0, "commonvoice_locale": "tig", "population": { "ER": 1094616 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Basque", "bcp_47": "eu", "speakers": 1088519, "scores": [], "commonvoice_hours": 335.0, "commonvoice_locale": "eu", "population": { "ES": 1000316, "FR": 88203 }, "language_family": null, "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hadothi", "bcp_47": "hoj", "speakers": 1087394, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1087394 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kabardian", "bcp_47": "kbd", "speakers": 1070873, "scores": [], "commonvoice_hours": 16.0, "commonvoice_locale": "kbd", "population": { "RU": 439338, "TR": 631535 }, "language_family": "Abkhaz-Adyge", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Khasi", "bcp_47": "kha", "speakers": 1060872, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 1060872 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sardinian", "bcp_47": "sc", "speakers": 1060846, "scores": [], "commonvoice_hours": 2.9, "commonvoice_locale": "sc", "population": { "IT": 1060846 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lozi", "bcp_47": "loz", "speakers": 1045596, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ZM": 1045596 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Frafra", "bcp_47": "gur", "speakers": 1026907, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GH": 1026907 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Najdi Arabic", "bcp_47": "ars", "speakers": 1025205, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SA": 1025205 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ronga", "bcp_47": "rng", "speakers": 1023339, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MZ": 1023339 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Luri", "bcp_47": "luz", "speakers": 1019080, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 1019080 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Newari", "bcp_47": "new", "speakers": 1000821, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "new", "population": { "NP": 1000821 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Talysh", "bcp_47": "tly", "speakers": 1000168, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AZ": 1000168 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yiddish", "bcp_47": "yi", "speakers": 997214, "scores": [], "commonvoice_hours": 0.5, "commonvoice_locale": "yi", "population": { "IL": 260264, "SE": 2959, "UA": 570998, "US": 162993 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bena", "bcp_47": "bez", "speakers": 995398, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 995398 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Shambala", "bcp_47": "ksb", "speakers": 995398, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 995398 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kachhi", "bcp_47": "kfr", "speakers": 994568, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 994568 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ngaju", "bcp_47": "nij", "speakers": 987996, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 987996 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kita Maninkakan", "bcp_47": "mwk", "speakers": 977670, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 977670 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Jumli", "bcp_47": "jml", "speakers": 970493, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 970493 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Okinawan", "bcp_47": "ryu", "speakers": 966404, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "JP": 966404 }, "language_family": "Japonic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mon", "bcp_47": "mnw", "speakers": 966114, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MM": 848852, "TH": 117262 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chimborazo Highland Quichua", "bcp_47": "qug", "speakers": 963579, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "EC": 963579 }, "language_family": "Quechuan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kachin", "bcp_47": "kac", "speakers": 962032, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MM": 962032 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Hindko", "bcp_47": "hnd", "speakers": 957354, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PK": 957354 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Limburgish", "bcp_47": "li", "speakers": 950422, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NL": 950422 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Manyika", "bcp_47": "mxc", "speakers": 945510, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ZW": 945510 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chechen", "bcp_47": "ce", "speakers": 935365, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 935365 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kuanyama", "bcp_47": "kj", "speakers": 920524, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NA": 920524 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "South Ndebele", "bcp_47": "nr", "speakers": 903418, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "nr", "population": { "ZA": 903418 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Welsh", "bcp_47": "cy", "speakers": 884910, "scores": [], "commonvoice_hours": 124.0, "commonvoice_locale": "cy", "population": { "AR": 30016, "GB": 854894 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Adangme", "bcp_47": "ada", "speakers": 880206, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GH": 880206 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Estonian", "bcp_47": "et", "speakers": 878449, "scores": [], "commonvoice_hours": 58.0, "commonvoice_locale": "et", "population": { "EE": 872320, "FI": 6129 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Parsi-Dari", "bcp_47": "prd", "speakers": 864342, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AF": 439726, "IR": 424616 }, "language_family": "Bookkeeping", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yucateco", "bcp_47": "yua", "speakers": 861955, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MX": 861955 }, "language_family": "Mayan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ewondo", "bcp_47": "ewo", "speakers": 860095, "scores": [], "commonvoice_hours": 19.0, "commonvoice_locale": "ewo", "population": { "CM": 860095 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Komering", "bcp_47": "kge", "speakers": 854483, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 854483 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tooro", "bcp_47": "ttj", "speakers": 821807, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UG": 821807 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Garo", "bcp_47": "grt", "speakers": 821563, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BD": 118735, "IN": 702828 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ga", "bcp_47": "gaa", "speakers": 821526, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GH": 821526 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mbunga", "bcp_47": "mgy", "speakers": 819739, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 819739 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tetum", "bcp_47": "tet", "speakers": 816395, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TL": 816395 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Iban", "bcp_47": "iba", "speakers": 816302, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MY": 816302 }, "language_family": "Bookkeeping", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Embu", "bcp_47": "ebu", "speakers": 802918, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 802918 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Swabian", "bcp_47": "swg", "speakers": 801597, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 801597 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hmong Njua", "bcp_47": "hnj", "speakers": 781687, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AU": 2190, "CN": 55761, "FR": 128912, "GF": 4788, "LA": 223422, "MM": 12450, "SR": 2316, "TH": 67598, "US": 116424, "VN": 167826 }, "language_family": "Hmong-Mien", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kalanga", "bcp_47": "kck", "speakers": 770954, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ZW": 770954 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dotyali", "bcp_47": "dty", "speakers": 758198, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 758198 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Picard", "bcp_47": "pcd", "speakers": 746330, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FR": 746330 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Frisian", "bcp_47": "fy", "speakers": 743057, "scores": [], "commonvoice_hours": 66.0, "commonvoice_locale": "fy-NL", "population": { "NL": 743057 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chakma", "bcp_47": "ccp", "speakers": 729137, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BD": 357832, "IN": 371305 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yao", "bcp_47": "yao", "speakers": 722357, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MZ": 722357 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Uab Meto", "bcp_47": "aoz", "speakers": 720970, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 720970 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Capiznon", "bcp_47": "cps", "speakers": 720595, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 720595 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Asu", "bcp_47": "asa", "speakers": 702634, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 702634 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tai Dam", "bcp_47": "blt", "speakers": 681177, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "VN": 681177 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Walloon", "bcp_47": "wa", "speakers": 679801, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BE": 679801 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Koyraboro Senni", "bcp_47": "ses", "speakers": 664816, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 664816 }, "language_family": "Songhay", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bagheli", "bcp_47": "bfy", "speakers": 654424, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 490653, "NP": 163771 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Asturian", "bcp_47": "ast", "speakers": 650205, "scores": [], "commonvoice_hours": 0.8, "commonvoice_locale": "ast", "population": { "ES": 650205 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Laki", "bcp_47": "lki", "speakers": 645417, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 645417 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Munda", "bcp_47": "unx", "speakers": 636523, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 636523 }, "language_family": "Bookkeeping", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lisu", "bcp_47": "lis", "speakers": 627309, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 627309 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "N’Ko", "bcp_47": "nqo", "speakers": 626370, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "nqo", "population": { "GN": 626370 }, "language_family": "Artificial Language", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gronings", "bcp_47": "gos", "speakers": 622094, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "gos", "population": { "NL": 622094 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mongo", "bcp_47": "lol", "speakers": 620858, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CD": 620858 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dangaura Tharu", "bcp_47": "thl", "speakers": 606558, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 606558 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Neapolitan", "bcp_47": "nap", "speakers": 605306, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IT": 605306 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nuer", "bcp_47": "nus", "speakers": 591427, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SS": 591427 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Breton", "bcp_47": "br", "speakers": 563140, "scores": [], "commonvoice_hours": 27.0, "commonvoice_locale": "br", "population": { "FR": 563140 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pijin", "bcp_47": "pis", "speakers": 561780, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SB": 561780 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Réunion Creole French", "bcp_47": "rcf", "speakers": 559185, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RE": 559185 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Avaric", "bcp_47": "av", "speakers": 552716, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 552716 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ndonga", "bcp_47": "ng", "speakers": 552315, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NA": 552315 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ossetic", "bcp_47": "os", "speakers": 541444, "scores": [], "commonvoice_hours": 0.7, "commonvoice_locale": "os", "population": { "GE": 87934, "RU": 453510 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Udmurt", "bcp_47": "udm", "speakers": 538544, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "udm", "population": { "RU": 538544 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ligurian", "bcp_47": "lij", "speakers": 536663, "scores": [], "commonvoice_hours": 5.1, "commonvoice_locale": "lij", "population": { "IT": 536663 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kabuverdianu", "bcp_47": "kea", "speakers": 530762, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CV": 530762 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rusyn", "bcp_47": "rue", "speakers": 527075, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "UA": 527075 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mari", "bcp_47": "chm", "speakers": 524371, "scores": [], "commonvoice_hours": 282.0, "commonvoice_locale": "mhr", "population": { "RU": 524371 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sicilian", "bcp_47": "scn", "speakers": 511702, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "scn", "population": { "IT": 511702 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Langi", "bcp_47": "lag", "speakers": 509409, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 509409 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Balti", "bcp_47": "bft", "speakers": 502520, "scores": [], "commonvoice_hours": 18.0, "commonvoice_locale": "bft", "population": { "IN": 82218, "PK": 420302 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Eastern Huasteca Nahuatl", "bcp_47": "nhe", "speakers": 501735, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "nhe", "population": { "MX": 501735 }, "language_family": "Uto-Aztecan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Huasteca Nahuatl", "bcp_47": "nhw", "speakers": 501735, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MX": 501735 }, "language_family": "Uto-Aztecan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Silesian", "bcp_47": "szl", "speakers": 497670, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PL": 497670 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kara-Kalpak", "bcp_47": "kaa", "speakers": 489046, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "kaa", "population": { "UZ": 489046 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gujari", "bcp_47": "gju", "speakers": 467002, "scores": [], "commonvoice_hours": 11.0, "commonvoice_locale": "gju", "population": { "PK": 467002 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sirmauri", "bcp_47": "srx", "speakers": 464132, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 464132 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Maltese", "bcp_47": "mt", "speakers": 457267, "scores": [], "commonvoice_hours": 8.7, "commonvoice_locale": "mt", "population": { "MT": 457267 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bantawa", "bcp_47": "bap", "speakers": 454918, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 454918 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yakut", "bcp_47": "sah", "speakers": 453510, "scores": [], "commonvoice_hours": 8.8, "commonvoice_locale": "sah", "population": { "RU": 453510 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Masalit", "bcp_47": "mls", "speakers": 451060, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SD": 451060 }, "language_family": "Maban", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Jju", "bcp_47": "kaj", "speakers": 449459, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 449459 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Adyghe", "bcp_47": "ady", "speakers": 444583, "scores": [], "commonvoice_hours": 11.0, "commonvoice_locale": "ady", "population": { "RU": 124715, "TR": 319868 }, "language_family": "Abkhaz-Adyge", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yemba", "bcp_47": "ybb", "speakers": 443920, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 443920 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mingrelian", "bcp_47": "xmf", "speakers": 439670, "scores": [], "commonvoice_hours": 9.5, "commonvoice_locale": "xmf", "population": { "GE": 439670 }, "language_family": "Kartvelian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Erzya", "bcp_47": "myv", "speakers": 439338, "scores": [], "commonvoice_hours": 3.8, "commonvoice_locale": "myv", "population": { "RU": 439338 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Taita", "bcp_47": "dav", "speakers": 438929, "scores": [], "commonvoice_hours": 9.3, "commonvoice_locale": "dav", "population": { "KE": 438929 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Mazahua", "bcp_47": "maz", "speakers": 437410, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MX": 437410 }, "language_family": "Otomanguean", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Vunjo", "bcp_47": "vun", "speakers": 433291, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 433291 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rombo", "bcp_47": "rof", "speakers": 433291, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 433291 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Machame", "bcp_47": "jmc", "speakers": 433291, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 433291 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Khmu", "bcp_47": "kjg", "speakers": 431949, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "LA": 431949 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Fang", "bcp_47": "fan", "speakers": 426451, "scores": [], "commonvoice_hours": 9.3, "commonvoice_locale": "fan", "population": { "GQ": 426451 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kinaray-a", "bcp_47": "krj", "speakers": 425806, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 425806 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kuy", "bcp_47": "kdt", "speakers": 421207, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KH": 18620, "LA": 71495, "TH": 331092 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Luxembourgish", "bcp_47": "lb", "speakers": 421015, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "lb", "population": { "LU": 421015 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sranan Tongo", "bcp_47": "srn", "speakers": 414507, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SR": 414507 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Jola-Fonyi", "bcp_47": "dyo", "speakers": 409146, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 409146 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Tamang", "bcp_47": "tdg", "speakers": 394263, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 394263 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pontic", "bcp_47": "pnt", "speakers": 392463, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GR": 392463 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Negeri Sembilan Malay", "bcp_47": "zmi", "speakers": 391825, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MY": 391825 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ngiemboon", "bcp_47": "nnh", "speakers": 388430, "scores": [], "commonvoice_hours": 23.0, "commonvoice_locale": "nnh", "population": { "CM": 388430 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ghomala", "bcp_47": "bbj", "speakers": 388430, "scores": [], "commonvoice_hours": 13.0, "commonvoice_locale": "bbj", "population": { "CM": 388430 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Divehi", "bcp_47": "dv", "speakers": 388044, "scores": [], "commonvoice_hours": 39.0, "commonvoice_locale": "dv", "population": { "IN": 3978, "MV": 384066 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Saurashtra", "bcp_47": "saz", "speakers": 384566, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 384566 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Fiji Hindi", "bcp_47": "hif", "speakers": 383749, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FJ": 383749 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nobiin", "bcp_47": "fia", "speakers": 378161, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SD": 378161 }, "language_family": "Nubian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Balkan Gagauz Turkish", "bcp_47": "bgx", "speakers": 377280, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TR": 377280 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kerinci", "bcp_47": "kvr", "speakers": 373836, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 373836 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Parkari Koli", "bcp_47": "kvx", "speakers": 373602, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PK": 373602 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dzongkha", "bcp_47": "dz", "speakers": 370341, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BT": 367689, "IN": 2652 }, "language_family": "Bookkeeping", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pökoot", "bcp_47": "pko", "speakers": 369343, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 369343 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dargwa", "bcp_47": "dar", "speakers": 368477, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "dar", "population": { "RU": 368477 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Limbu", "bcp_47": "lif", "speakers": 368085, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 34478, "NP": 333607 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Fijian", "bcp_47": "fj", "speakers": 365030, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FJ": 365030 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rana Tharu", "bcp_47": "thr", "speakers": 363935, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 363935 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kom", "bcp_47": "bkm", "speakers": 360685, "scores": [], "commonvoice_hours": 13.0, "commonvoice_locale": "bkm", "population": { "CM": 360685 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Icelandic", "bcp_47": "is", "speakers": 350734, "scores": [], "commonvoice_hours": 0.1, "commonvoice_locale": "is", "population": { "IS": 350734 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Khowar", "bcp_47": "khw", "speakers": 350252, "scores": [], "commonvoice_hours": 18.0, "commonvoice_locale": "khw", "population": { "PK": 350252 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tolaki", "bcp_47": "lbw", "speakers": 347134, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 347134 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Naxi", "bcp_47": "nxq", "speakers": 334565, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 334565 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Eastern Magar", "bcp_47": "mgp", "speakers": 333607, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 333607 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bamun", "bcp_47": "bax", "speakers": 332940, "scores": [], "commonvoice_hours": 11.0, "commonvoice_locale": "bax", "population": { "CM": 332940 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Basaa", "bcp_47": "bas", "speakers": 332940, "scores": [], "commonvoice_hours": 12.0, "commonvoice_locale": "bas", "population": { "CM": 332940 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Koyra Chiini", "bcp_47": "khq", "speakers": 332408, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 332408 }, "language_family": "Songhay", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Indus Kohistani", "bcp_47": "mvy", "speakers": 326901, "scores": [], "commonvoice_hours": 23.0, "commonvoice_locale": "mvy", "population": { "PK": 326901 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gayo", "bcp_47": "gay", "speakers": 320431, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 320431 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ngazidja Comorian", "bcp_47": "zdj", "speakers": 313124, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KM": 313124 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Buriat", "bcp_47": "bua", "speakers": 311788, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "bxr", "population": { "RU": 311788 }, "language_family": "Mongolic-Khitan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rinconada Bikol", "bcp_47": "bto", "speakers": 305707, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 305707 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Medumba", "bcp_47": "byv", "speakers": 305195, "scores": [], "commonvoice_hours": 14.0, "commonvoice_locale": "byv", "population": { "CM": 305195 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ao Naga", "bcp_47": "njo", "speakers": 305001, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 305001 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Badaga", "bcp_47": "bfq", "speakers": 305001, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 305001 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kochila Tharu", "bcp_47": "thq", "speakers": 303279, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 303279 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Moksha", "bcp_47": "mdf", "speakers": 297616, "scores": [], "commonvoice_hours": 0.5, "commonvoice_locale": "mdf", "population": { "RU": 297616 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tae'", "bcp_47": "rob", "speakers": 293729, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 293729 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nzima", "bcp_47": "nzi", "speakers": 293402, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GH": 293402 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nama", "bcp_47": "naq", "speakers": 289308, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NA": 289308 }, "language_family": "Khoe-Kwadi", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ndzwani Comorian", "bcp_47": "wni", "speakers": 287736, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KM": 287736 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kumyk", "bcp_47": "kum", "speakers": 283444, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 283444 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mundang", "bcp_47": "mua", "speakers": 277450, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 277450 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mapuche", "bcp_47": "arn", "speakers": 272802, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "arn", "population": { "CL": 272802 }, "language_family": "Araucanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Cham", "bcp_47": "cja", "speakers": 270832, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KH": 270832 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bislama", "bcp_47": "bi", "speakers": 268500, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "VU": 268500 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lü", "bcp_47": "khb", "speakers": 264864, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 264864 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tai Nüa", "bcp_47": "tdd", "speakers": 264864, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 264864 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Wadiyara Koli", "bcp_47": "kxp", "speakers": 256851, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PK": 256851 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kachi Koli", "bcp_47": "gjk", "speakers": 256851, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PK": 256851 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lezghian", "bcp_47": "lez", "speakers": 255100, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 255100 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Komi", "bcp_47": "kv", "speakers": 255100, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "kpv", "population": { "RU": 255100 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Samoan", "bcp_47": "sm", "speakers": 252717, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AS": 48943, "WS": 203774 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Magar", "bcp_47": "mrd", "speakers": 251722, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 251722 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Samburu", "bcp_47": "saq", "speakers": 246228, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KE": 246228 }, "language_family": "Nilotic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Crimean Tatar", "bcp_47": "crh", "speakers": 245968, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "crh", "population": { "UA": 245968 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mandar", "bcp_47": "mdr", "speakers": 245664, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 245664 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sangir", "bcp_47": "sxn", "speakers": 245664, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 245664 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Extremaduran", "bcp_47": "ext", "speakers": 245077, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ES": 245077 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Huasteca Nahuatl", "bcp_47": "nch", "speakers": 244435, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MX": 244435 }, "language_family": "Uto-Aztecan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zeelandic", "bcp_47": "zea", "speakers": 241926, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NL": 241926 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Karachay-Balkar", "bcp_47": "krc", "speakers": 240927, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "krc", "population": { "RU": 240927 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Colognian", "bcp_47": "ksh", "speakers": 240479, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 240479 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Herero", "bcp_47": "hz", "speakers": 239336, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NA": 239336 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Saafi-Saafi", "bcp_47": "sav", "speakers": 236046, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 236046 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zaghawa", "bcp_47": "zag", "speakers": 232364, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SD": 232364 }, "language_family": "Saharan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ingush", "bcp_47": "inh", "speakers": 226755, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 226755 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Saho", "bcp_47": "ssy", "speakers": 218923, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ER": 218923 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tomo Kan Dogon", "bcp_47": "dtm", "speakers": 215087, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 215087 }, "language_family": "Dogon", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Papiamento", "bcp_47": "pap", "speakers": 211640, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "pap-AW", "population": { "AW": 72851, "BQ": 16200, "CW": 122589 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Syriac", "bcp_47": "syr", "speakers": 210659, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "syr", "population": { "IQ": 194364, "SY": 16295 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nyasa Tonga", "bcp_47": "tog", "speakers": 207727, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MW": 207727 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mafa", "bcp_47": "maf", "speakers": 205313, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 205313 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Punu", "bcp_47": "puu", "speakers": 200782, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GA": 200782 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tyap", "bcp_47": "kcg", "speakers": 199046, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 199046 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Xaasongaxango", "bcp_47": "kao", "speakers": 195534, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 195534 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tuvinian", "bcp_47": "tyv", "speakers": 184239, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "tyv", "population": { "RU": 184239 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Dusun", "bcp_47": "dtp", "speakers": 182852, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MY": 182852 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Riang (India)", "bcp_47": "ria", "speakers": 172392, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 172392 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Comorian", "bcp_47": "swb", "speakers": 170720, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "YT": 170720 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bomu", "bcp_47": "bmq", "speakers": 168159, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 168159 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Latgalian", "bcp_47": "ltg", "speakers": 167429, "scores": [], "commonvoice_hours": 28.0, "commonvoice_locale": "ltg", "population": { "LV": 167429 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Navajo", "bcp_47": "nv", "speakers": 166320, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 166320 }, "language_family": "Athabaskan-Eyak-Tlingit", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Jenaama Bozo", "bcp_47": "bze", "speakers": 166204, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ML": 166204 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Corsican", "bcp_47": "co", "speakers": 162836, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "co", "population": { "FR": 162836 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bafut", "bcp_47": "bfd", "speakers": 158146, "scores": [], "commonvoice_hours": 11.0, "commonvoice_locale": "bfd", "population": { "CM": 158146 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sherpa", "bcp_47": "xsr", "speakers": 157705, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 157705 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kirmanjki", "bcp_47": "kiu", "speakers": 155833, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TR": 155833 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hiri Motu", "bcp_47": "ho", "speakers": 152449, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PG": 152449 }, "language_family": "Pidgin", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kako", "bcp_47": "kkj", "speakers": 149823, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 149823 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Akoose", "bcp_47": "bss", "speakers": 149823, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 149823 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Selayar", "bcp_47": "sly", "speakers": 144194, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 144194 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Māori", "bcp_47": "mi", "speakers": 137913, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NZ": 137913 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rajbanshi", "bcp_47": "rjs", "speakers": 133443, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 133443 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Duala", "bcp_47": "dua", "speakers": 133176, "scores": [], "commonvoice_hours": 14.0, "commonvoice_locale": "dua", "population": { "CM": 133176 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Wayuu", "bcp_47": "guc", "speakers": 132529, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "guc", "population": { "CO": 132529 }, "language_family": "Arawakan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Vai", "bcp_47": "vai", "speakers": 131906, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "LR": 131906 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Eastern Tamang", "bcp_47": "taj", "speakers": 130410, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 130410 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Metaʼ", "bcp_47": "mgo", "speakers": 130401, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 130401 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pennsylvania German", "bcp_47": "pdc", "speakers": 129729, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 129729 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rwa", "bcp_47": "rwk", "speakers": 128816, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 128816 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Torwali", "bcp_47": "trw", "speakers": 123756, "scores": [], "commonvoice_hours": 19.0, "commonvoice_locale": "trw", "population": { "PK": 123756 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mandjak", "bcp_47": "mfv", "speakers": 121170, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 121170 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tshangla", "bcp_47": "tsj", "speakers": 117348, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BT": 117348 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sangu", "bcp_47": "sbp", "speakers": 117106, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TZ": 117106 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Karelian", "bcp_47": "krl", "speakers": 116212, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 116212 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ladino", "bcp_47": "lad", "speakers": 112781, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IL": 112781 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ifè", "bcp_47": "ife", "speakers": 111910, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TG": 111910 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gagauz", "bcp_47": "gag", "speakers": 111028, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MD": 111028 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lak", "bcp_47": "lbe", "speakers": 110543, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 110543 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sassarese Sardinian", "bcp_47": "sdc", "speakers": 106085, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IT": 106085 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tongan", "bcp_47": "to", "speakers": 100790, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TO": 100790 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Balanta-Ganja", "bcp_47": "bjt", "speakers": 95992, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 95992 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ngomba", "bcp_47": "jgo", "speakers": 94333, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 94333 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Seselwa Creole French", "bcp_47": "crs", "speakers": 94061, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SC": 94061 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Abkhazian", "bcp_47": "ab", "speakers": 91953, "scores": [], "commonvoice_hours": 67.0, "commonvoice_locale": "ab", "population": { "GE": 87934, "TR": 4019 }, "language_family": "Abkhaz-Adyge", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tahitian", "bcp_47": "ty", "speakers": 91488, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ty", "population": { "PF": 91488 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Inuktitut", "bcp_47": "iu", "speakers": 90466, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 90466 }, "language_family": "Eskimo-Aleut", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Plautdietsch", "bcp_47": "pdt", "speakers": 90466, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 90466 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bishnupriya", "bcp_47": "bpy", "speakers": 90174, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 90174 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bafia", "bcp_47": "ksf", "speakers": 88784, "scores": [], "commonvoice_hours": 20.0, "commonvoice_locale": "ksf", "population": { "CM": 88784 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gurung", "bcp_47": "gvr", "speakers": 87951, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 87951 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Eastern Cham", "bcp_47": "cjm", "speakers": 87862, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "VN": 87862 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Lawa", "bcp_47": "lcp", "speakers": 87751, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 80853, "TH": 6898 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mankanya", "bcp_47": "knf", "speakers": 83151, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GW": 50105, "SN": 33046 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lepcha", "bcp_47": "lep", "speakers": 79743, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BT": 30510, "IN": 46413, "NP": 2820 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Blin", "bcp_47": "byn", "speakers": 79056, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ER": 79056 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bateri", "bcp_47": "btv", "speakers": 78843, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 34478, "PK": 44365 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kathoriya Tharu", "bcp_47": "tkt", "speakers": 72787, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 72787 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Scottish Gaelic", "bcp_47": "gd", "speakers": 72337, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GB": 72337 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Faroese", "bcp_47": "fo", "speakers": 71351, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "fo", "population": { "DK": 22304, "FO": 49047 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Võro", "bcp_47": "vro", "speakers": 70031, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "EE": 70031 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kenyang", "bcp_47": "ken", "speakers": 69362, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 69362 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gilbertese", "bcp_47": "gil", "speakers": 67078, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "KI": 67078 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bube", "bcp_47": "bvb", "speakers": 66058, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GQ": 66058 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mentawai", "bcp_47": "mwv", "speakers": 64086, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ID": 64086 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Arpitan", "bcp_47": "frp", "speakers": 63777, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FR": 63777 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Komi-Permyak", "bcp_47": "koi", "speakers": 63775, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 63775 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Koro", "bcp_47": "kfo", "speakers": 63207, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CI": 63207 }, "language_family": "Mande", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Marshallese", "bcp_47": "mh", "speakers": 56879, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "MH": 56879 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tornedalen Finnish", "bcp_47": "fit", "speakers": 56114, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SE": 56114 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kalaallisut", "bcp_47": "kl", "speakers": 55440, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DK": 7043, "GL": 48397 }, "language_family": "Eskimo-Aleut", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Braj", "bcp_47": "bra", "speakers": 54370, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 54370 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Guianese Creole French", "bcp_47": "gcr", "speakers": 51872, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GF": 51872 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Sami", "bcp_47": "se", "speakers": 51530, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FI": 2006, "NO": 15856, "SE": 33668 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Anii", "bcp_47": "blo", "speakers": 51507, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BJ": 38594, "TG": 12913 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kaingang", "bcp_47": "kgp", "speakers": 50812, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BR": 50812 }, "language_family": "Nuclear-Macro-Je", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kashubian", "bcp_47": "csb", "speakers": 49767, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PL": 49767 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Koro Wachi", "bcp_47": "bqv", "speakers": 46718, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CI": 46718 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chamorro", "bcp_47": "ch", "speakers": 46325, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GU": 37067, "MP": 9258 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Atsam", "bcp_47": "cch", "speakers": 44946, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 44946 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bushi", "bcp_47": "buc", "speakers": 44620, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "YT": 44620 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Romansh", "bcp_47": "rm", "speakers": 42020, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CH": 42020 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Aghem", "bcp_47": "agq", "speakers": 38843, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 38843 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kuvi", "bcp_47": "kxv", "speakers": 38457, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 38457 }, "language_family": "Dravidian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Noon", "bcp_47": "snf", "speakers": 37767, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 37767 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Friulian", "bcp_47": "fur", "speakers": 37442, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IT": 37442 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Thulung", "bcp_47": "tdh", "speakers": 36393, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NP": 36393 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Emilian", "bcp_47": "egl", "speakers": 31201, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IT": 31201 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chuukese", "bcp_47": "chk", "speakers": 30731, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FM": 30731 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Western Mari", "bcp_47": "mrj", "speakers": 29762, "scores": [], "commonvoice_hours": 34.0, "commonvoice_locale": "mrj", "population": { "RU": 29762 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hawaiian", "bcp_47": "haw", "speakers": 29605, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 29605 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mru", "bcp_47": "mro", "speakers": 29277, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BD": 29277 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Cajun French", "bcp_47": "frc", "speakers": 27942, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 27942 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nheengatu", "bcp_47": "yrl", "speakers": 26171, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BR": 21172, "CO": 2994, "VE": 2005 }, "language_family": "Tupian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Aragonese", "bcp_47": "an", "speakers": 26008, "scores": [], "commonvoice_hours": 13.0, "commonvoice_locale": "an", "population": { "ES": 26008 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Cherokee", "bcp_47": "chr", "speakers": 25613, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 25613 }, "language_family": "Iroquoian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sinte Romani", "bcp_47": "rmo", "speakers": 24372, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CH": 24372 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ojibwa", "bcp_47": "oj", "speakers": 23747, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 23747 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Pohnpeian", "bcp_47": "pon", "speakers": 23560, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FM": 23560 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Laz", "bcp_47": "lzz", "speakers": 22965, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "lzz", "population": { "TR": 22965 }, "language_family": "Kartvelian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Muslim Tat", "bcp_47": "ttt", "speakers": 22453, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AZ": 22453 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Central Yupik", "bcp_47": "esu", "speakers": 20956, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "esu", "population": { "US": 20956 }, "language_family": "Eskimo-Aleut", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dakota", "bcp_47": "dak", "speakers": 20832, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 1206, "US": 19626 }, "language_family": "Siouan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Altai", "bcp_47": "alt", "speakers": 19841, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 19841 }, "language_family": "Turkic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Amo", "bcp_47": "amo", "speakers": 18620, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 18620 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Guajajára", "bcp_47": "gub", "speakers": 17784, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BR": 17784 }, "language_family": "Tupian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hanunoo", "bcp_47": "hnn", "speakers": 17469, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 17469 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tsakhur", "bcp_47": "tkr", "speakers": 16329, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AZ": 16329 }, "language_family": "Nakh-Daghestanian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Palauan", "bcp_47": "pau", "speakers": 16047, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PW": 16047 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Sanskrit", "bcp_47": "sa", "speakers": 15913, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 15913 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Bassari", "bcp_47": "bsc", "speakers": 15264, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 15264 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Oji-Cree", "bcp_47": "ojs", "speakers": 15078, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 15078 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Khamti", "bcp_47": "kht", "speakers": 13527, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IN": 9283, "MM": 4244 }, "language_family": "Tai-Kadai", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Upper Sorbian", "bcp_47": "hsb", "speakers": 12826, "scores": [], "commonvoice_hours": 2.9, "commonvoice_locale": "hsb", "population": { "DE": 12826 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chipewyan", "bcp_47": "chp", "speakers": 12816, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 12816 }, "language_family": "Athabaskan-Eyak-Tlingit", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Innu-aimun", "bcp_47": "moe", "speakers": 12062, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 12062 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lower Silesian", "bcp_47": "sli", "speakers": 11868, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PL": 11868 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Walser", "bcp_47": "wae", "speakers": 11377, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CH": 10085, "LI": 1292 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Choctaw", "bcp_47": "cho", "speakers": 10977, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 10977 }, "language_family": "Muskogean", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tagbanwa", "bcp_47": "tbw", "speakers": 10045, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 10045 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Xavánte", "bcp_47": "xav", "speakers": 9951, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BR": 9951 }, "language_family": "Nuclear-Macro-Je", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tuvalu", "bcp_47": "tvl", "speakers": 9868, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TV": 9868 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern Frisian", "bcp_47": "frr", "speakers": 9619, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 9619 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Roviana", "bcp_47": "rug", "speakers": 9591, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SB": 9591 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Wallisian", "bcp_47": "wls", "speakers": 9512, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "WF": 9512 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tavringer Romani", "bcp_47": "rmu", "speakers": 9488, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SE": 9488 }, "language_family": "Speech Register", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Cree", "bcp_47": "cr", "speakers": 9047, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 9047 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kwasio", "bcp_47": "nmg", "speakers": 8878, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 8878 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lakota", "bcp_47": "lkt", "speakers": 8316, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 8316 }, "language_family": "Siouan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kosraean", "bcp_47": "kos", "speakers": 7990, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FM": 7990 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Inupiaq", "bcp_47": "ik", "speakers": 7983, "scores": [], "commonvoice_hours": 2.8, "commonvoice_locale": "ipk", "population": { "US": 7983 }, "language_family": "Eskimo-Aleut", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Zoroastrian Dari", "bcp_47": "gbz", "speakers": 7983, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IR": 7983 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tasawaq", "bcp_47": "twq", "speakers": 7970, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NE": 7970 }, "language_family": "Songhay", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Buhid", "bcp_47": "bku", "speakers": 7970, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PH": 7970 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mi'kmaw", "bcp_47": "mic", "speakers": 7916, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 7916 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Hassaniyya", "bcp_47": "mey", "speakers": 7239, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 7239 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lower Sorbian", "bcp_47": "dsb", "speakers": 6974, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "dsb", "population": { "DE": 6974 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Nauru", "bcp_47": "na", "speakers": 6930, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NR": 6930 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Eastern Lawa", "bcp_47": "lwl", "speakers": 6898, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TH": 6898 }, "language_family": "Austroasiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yapese", "bcp_47": "yap", "speakers": 6556, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FM": 6556 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Atikamekw", "bcp_47": "atj", "speakers": 6408, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 6408 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Piedmontese", "bcp_47": "pms", "speakers": 6178, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IT": 6178 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kalo Finnish Romani", "bcp_47": "rmf", "speakers": 5015, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FI": 5015 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Siksiká", "bcp_47": "bla", "speakers": 4900, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 4900 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "East Futuna", "bcp_47": "fud", "speakers": 4756, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "WF": 4756 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Taroko", "bcp_47": "trv", "speakers": 4721, "scores": [], "commonvoice_hours": 5.7, "commonvoice_locale": "trv", "population": { "TW": 4721 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Plains Cree", "bcp_47": "crk", "speakers": 4146, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 4146 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Safaliba", "bcp_47": "saf", "speakers": 4108, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GH": 4108 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Muscogee", "bcp_47": "mus", "speakers": 3992, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 3992 }, "language_family": "Muskogean", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Veps", "bcp_47": "vep", "speakers": 3543, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 3543 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ménik", "bcp_47": "tnr", "speakers": 3305, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SN": 3305 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Virgin Islands Creole English", "bcp_47": "vic", "speakers": 3113, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SX": 3113 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Turoyo", "bcp_47": "tru", "speakers": 3035, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TR": 3035 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ulithian", "bcp_47": "uli", "speakers": 2971, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FM": 2971 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Rotuman", "bcp_47": "rtm", "speakers": 2527, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FJ": 2527 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Warlpiri", "bcp_47": "wbp", "speakers": 2496, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "AU": 2496 }, "language_family": "Pama-Nyungan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Yangben", "bcp_47": "yav", "speakers": 2303, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CM": 2303 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Slave", "bcp_47": "den", "speakers": 2299, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 2299 }, "language_family": "Athabaskan-Eyak-Tlingit", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Dogrib", "bcp_47": "dgr", "speakers": 2111, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 2111 }, "language_family": "Athabaskan-Eyak-Tlingit", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Eastern Frisian", "bcp_47": "frs", "speakers": 2004, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 2004 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Cornish", "bcp_47": "kw", "speakers": 1973, "scores": [], "commonvoice_hours": 2.9, "commonvoice_locale": "kw", "population": { "GB": 1973 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Swampy Cree", "bcp_47": "csw", "speakers": 1809, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 1809 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Mohawk", "bcp_47": "moh", "speakers": 1772, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 1772 }, "language_family": "Iroquoian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Manx", "bcp_47": "gv", "speakers": 1719, "scores": [], "commonvoice_hours": 4.5, "commonvoice_locale": "gv", "population": { "IM": 1719 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lule Sami", "bcp_47": "smj", "speakers": 1530, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SE": 1530 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Naskapi", "bcp_47": "nsk", "speakers": 1395, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 1395 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tokelau", "bcp_47": "tkl", "speakers": 1285, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "TK": 1285 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Niuean", "bcp_47": "niu", "speakers": 1120, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NU": 1120 }, "language_family": "Austronesian", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Saterland Frisian", "bcp_47": "stq", "speakers": 962, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 962 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Seri", "bcp_47": "sei", "speakers": 901, "scores": [], "commonvoice_hours": 1.2, "commonvoice_locale": "sei", "population": { "MX": 901 }, "language_family": null, "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chilcotin", "bcp_47": "clc", "speakers": 867, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 867 }, "language_family": "Athabaskan-Eyak-Tlingit", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Latin", "bcp_47": "la", "speakers": 820, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "VA": 820 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Halkomelem", "bcp_47": "hur", "speakers": 716, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 716 }, "language_family": "Salishan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Michif", "bcp_47": "crg", "speakers": 678, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 678 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Skolt Sami", "bcp_47": "sms", "speakers": 613, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FI": 613 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Inari Sami", "bcp_47": "smn", "speakers": 613, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "FI": 613 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lillooet", "bcp_47": "lil", "speakers": 528, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 528 }, "language_family": "Salishan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Okanagan", "bcp_47": "oka", "speakers": 490, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 490 }, "language_family": "Salishan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Maliseet-Passamaquoddy", "bcp_47": "pqm", "speakers": 490, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 490 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Kwakʼwala", "bcp_47": "kwk", "speakers": 377, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 377 }, "language_family": "Wakashan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Northern East Cree", "bcp_47": "crl", "speakers": 377, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 377 }, "language_family": "Algic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Gwichʼin", "bcp_47": "gwi", "speakers": 302, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CA": 302 }, "language_family": "Athabaskan-Eyak-Tlingit", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Esperanto", "bcp_47": "eo", "speakers": 301, "scores": [], "commonvoice_hours": 1436.0, "commonvoice_locale": "eo", "population": { "SM": 301 }, "language_family": "Artificial Language", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Southern Sami", "bcp_47": "sma", "speakers": 296, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "SE": 296 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Tsakonian", "bcp_47": "tsd", "speakers": 202, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "GR": 202 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ingrian", "bcp_47": "izh", "speakers": 142, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "izh", "population": { "RU": 142 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Interlingua", "bcp_47": "ia", "speakers": 136, "scores": [], "commonvoice_hours": 14.0, "commonvoice_locale": "ia", "population": { "FR": 136, "SE": 0 }, "language_family": "Artificial Language", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Araona", "bcp_47": "aro", "speakers": 105, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "BO": 105 }, "language_family": "Pano-Tacanan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Prussian", "bcp_47": "prg", "speakers": 38, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "PL": 38 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Interlingue", "bcp_47": "ie", "speakers": 1, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "ie", "population": { "EE": 1 }, "language_family": "Artificial Language", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Literary Chinese", "bcp_47": "lzh", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "CN": 0 }, "language_family": "Sino-Tibetan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Ido", "bcp_47": "io", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 0 }, "language_family": "Artificial Language", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Lojban", "bcp_47": "jbo", "speakers": 0, "scores": [], "commonvoice_hours": 0.0, "commonvoice_locale": "jbo", "population": { "US": 0 }, "language_family": "Artificial Language", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Jutish", "bcp_47": "jut", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DK": 0 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Votic", "bcp_47": "vot", "speakers": 0, "scores": [], "commonvoice_hours": 0.1, "commonvoice_locale": "vot", "population": { "RU": 0 }, "language_family": "Uralic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Geez", "bcp_47": "gez", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "ET": 0 }, "language_family": "Afro-Asiatic", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Osage", "bcp_47": "osa", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 0 }, "language_family": "Siouan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Romagnol", "bcp_47": "rgn", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "IT": 0 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Church Slavic", "bcp_47": "cu", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "RU": 0 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Samogitian", "bcp_47": "sgs", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "LT": 0 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Obolo", "bcp_47": "ann", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "NG": 0 }, "language_family": "Atlantic-Congo", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Chickasaw", "bcp_47": "cic", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 0 }, "language_family": "Muskogean", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Caddo", "bcp_47": "cad", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "US": 0 }, "language_family": "Caddoan", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null }, { "language_name": "Palatine German", "bcp_47": "pfl", "speakers": 0, "scores": [], "commonvoice_hours": null, "commonvoice_locale": null, "population": { "DE": 0 }, "language_family": "Indo-European", "mt_bleu": null, "mt_chrf": null, "cls_acc": null, "mlm_chrf": null, "asr_wer": null, "asr_chrf": null, "t2t_score": null, "s2t_score": null } ]