{ "ukusnews_short_test": { "wer": { "whisper_large_v3": 0.06168908700151238, "Qwen-Audio-Chat": 0.10399586086125925, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.06877338215394412, "WavLLM_fairseq": 0.2066783411605508, "Qwen2-Audio-7B-Instruct": 0.1194380323171217, "SALMONN_7B": 0.09042426172092653, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.10144869855926132, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.0700867627159118 } }, "imda_part6_30s_asr_test": { "wer": { "whisper_large_v3": 0.1698509342851144, "Qwen-Audio-Chat": 0.31394240863063033, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.1789273082575623, "WavLLM_fairseq": 0.42541061709652933, "Qwen2-Audio-7B-Instruct": 0.2245352799625317, "SALMONN_7B": 0.24872817713464365, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.11292172031202054, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.17467982364056267 } }, "covost2_en_id_test": { "bleu": { "whisper_large_v3": 1.600581653970121, "Qwen-Audio-Chat": 4.102230932924371, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 27.620150160643625, "WavLLM_fairseq": 13.841886973016162, "Qwen2-Audio-7B-Instruct": 16.325186897428104, "SALMONN_7B": 14.102682915273142, "MERaLiON-AudioLLM-Whisper-SEA-LION": 37.60224687716629, "cascade_whisper_large_v3_llama_3_8b_instruct": 10.930203684508578 } }, "imda_part3_30s_asr_test": { "wer": { "whisper_large_v3": 0.27026366524560785, "Qwen-Audio-Chat": 0.6412550574306894, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.3035544573275043, "WavLLM_fairseq": 0.7540934640345399, "Qwen2-Audio-7B-Instruct": 0.35076166942732234, "SALMONN_7B": 0.6569229098215983, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.2919053954978684, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.29992939962527493 } }, "gigaspeech_test": { "wer": { "whisper_large_v3": 0.09459022434812692, "Qwen-Audio-Chat": 0.13018910022587737, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.09948381629977261, "WavLLM_fairseq": 0.15491778414546403, "Qwen2-Audio-7B-Instruct": 0.11723812890302816, "SALMONN_7B": 0.10765150204693537, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.14457154747310655, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.09515429104337297 } }, "covost2_ta_en_test": { "bleu": { "whisper_large_v3": 2.451098639578599, "Qwen-Audio-Chat": 0.01699144301093184, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 2.8327095799289337, "WavLLM_fairseq": 0.1695522548322915, "Qwen2-Audio-7B-Instruct": 0.04425838146050298, "SALMONN_7B": 0.3649023706010388, "MERaLiON-AudioLLM-Whisper-SEA-LION": 5.023057608950299, "cascade_whisper_large_v3_llama_3_8b_instruct": 2.4245628096245917 } }, "librispeech_test_other": { "wer": { "whisper_large_v3": 0.03660128246354058, "Qwen-Audio-Chat": 0.043467569561352074, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.05307658841999735, "WavLLM_fairseq": 0.04798834811886432, "Qwen2-Audio-7B-Instruct": 0.060415760304159495, "SALMONN_7B": 0.09671439650443565, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.041576030415949455, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.03714982881570734 } }, "parliament_test": { "wer": { "whisper_large_v3": 0.0753619074652285, "Qwen-Audio-Chat": 0.26279685873781816, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.06282524363705176, "WavLLM_fairseq": 0.5216434856656259, "Qwen2-Audio-7B-Instruct": 0.23270886555019396, "SALMONN_7B": 0.3010928186204939, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.058922319992430694, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.07517267480367111 } }, "earnings22_test": { "wer": { "whisper_large_v3": 0.15887899737116104, "Qwen-Audio-Chat": 0.3664994875132684, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.1448629161356777, "WavLLM_fairseq": 0.6671766188447099, "Qwen2-Audio-7B-Instruct": 0.23542555661330924, "SALMONN_7B": 0.3597423676988383, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.1652245056860175, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.15611126487402763 } }, "imda_part2_asr_test": { "wer": { "whisper_large_v3": 0.3171008846684522, "Qwen-Audio-Chat": 0.45479263046830615, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.32988393799204613, "WavLLM_fairseq": 0.4463923382842302, "Qwen2-Audio-7B-Instruct": 0.1905689473257041, "SALMONN_7B": 0.42346400454508565, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.048088629169710254, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.31912994075156237 } }, "ukusnews_test": { "wer": { "whisper_large_v3": 0.07135564378899603, "Qwen-Audio-Chat": 0.3158631121194933, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.07388920400831915, "WavLLM_fairseq": 0.5911892607298166, "Qwen2-Audio-7B-Instruct": 0.13843826810361126, "SALMONN_7B": 0.18918510115333712, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.12554358101720553, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.07642276422764227 } }, "earnings21_test": { "wer": { "whisper_large_v3": 0.11863959266711877, "Qwen-Audio-Chat": 0.2655529121410546, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.11416493424197618, "WavLLM_fairseq": 0.6447482518259942, "Qwen2-Audio-7B-Instruct": 0.18872219319407232, "SALMONN_7B": 0.2577708974886327, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.13488732754499672, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.11773910240019567 } }, "covost2_zh_en_test": { "bleu": { "whisper_large_v3": 14.673689493155793, "Qwen-Audio-Chat": 9.898238298955656, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 15.209998552437538, "WavLLM_fairseq": 2.368659001743569, "Qwen2-Audio-7B-Instruct": 16.466557744958333, "SALMONN_7B": 5.296039450108202, "MERaLiON-AudioLLM-Whisper-SEA-LION": 18.76473995941838, "cascade_whisper_large_v3_llama_3_8b_instruct": 14.154700735606419 } }, "covost2_en_ta_test": { "bleu": { "whisper_large_v3": 0.02107778621423822, "Qwen-Audio-Chat": 0.03451483807236294, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 8.433062902024755, "WavLLM_fairseq": 0.0033159224040994286, "Qwen2-Audio-7B-Instruct": 0.03245972071872916, "SALMONN_7B": 0.00046745670226766583, "MERaLiON-AudioLLM-Whisper-SEA-LION": 14.407399367512914, "cascade_whisper_large_v3_llama_3_8b_instruct": 1.0368044741318085 } }, "librispeech_test_clean": { "wer": { "whisper_large_v3": 0.01878749009695552, "Qwen-Audio-Chat": 0.020258799562379748, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.032349945297468596, "WavLLM_fairseq": 0.02103218017882069, "Qwen2-Audio-7B-Instruct": 0.035141660693401744, "SALMONN_7B": 0.10270871845172973, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.022918474365262006, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.018334779492209605 } }, "tedlium3_test": { "wer": { "whisper_large_v3": 0.037649480146197796, "Qwen-Audio-Chat": 0.04052375714133636, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.04900464852205386, "WavLLM_fairseq": 0.06621482559171073, "Qwen2-Audio-7B-Instruct": 0.06114048472375004, "SALMONN_7B": 0.0459884319222171, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.07884745040985061, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.038146268762641496 } }, "imda_part1_asr_test": { "wer": { "whisper_large_v3": 0.06844171360300393, "Qwen-Audio-Chat": 0.10550313315290274, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.07041669714480775, "WavLLM_fairseq": 0.10077292565771828, "Qwen2-Audio-7B-Instruct": 0.07197717796796138, "SALMONN_7B": 0.0925804013361617, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.042254894789457, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.06922195401458074 } }, "common_voice_15_en_test": { "wer": { "whisper_large_v3": 0.10001863741235596, "Qwen-Audio-Chat": 0.11272421128398918, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.10600831614192711, "WavLLM_fairseq": 0.14533325621300636, "Qwen2-Audio-7B-Instruct": 0.11438872500819404, "SALMONN_7B": 0.3062255383962828, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.07811646454714301, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.09876543209876543 } }, "mediacorp_test": { "wer": { "whisper_large_v3": 0.12054884024828487, "Qwen-Audio-Chat": 0.4498529892192094, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.12455080039202875, "WavLLM_fairseq": 0.3595230316889905, "Qwen2-Audio-7B-Instruct": 0.18694870957203527, "SALMONN_7B": 0.32089186540346293, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.170859196341065, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.13598497223129696 } }, "idpc_short_test": { "wer": { "whisper_large_v3": 0.1662526275558953, "Qwen-Audio-Chat": 0.6008025988916491, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.16931014714313014, "WavLLM_fairseq": 0.36728454041658704, "Qwen2-Audio-7B-Instruct": 0.21326199120963119, "SALMONN_7B": 0.26313777947639977, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.24918784635964075, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.15803554366520162 } }, "seame_dev_man": { "wer": { "whisper_large_v3": 0.7225930420711975, "Qwen-Audio-Chat": 0.8783373786407767, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.7824973031283711, "WavLLM_fairseq": 1.2913969795037756, "Qwen2-Audio-7B-Instruct": 0.5522518878101402, "SALMONN_7B": 1.2721817691477886, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.388282092772384, "gemini-1.5-flash": 0.9690871089536138, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.6848705501618123 } }, "cna_test": { "wer": { "whisper_large_v3": 0.13841717398269784, "Qwen-Audio-Chat": 0.19753284203780838, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.15171419416853574, "WavLLM_fairseq": 0.26946491509131687, "Qwen2-Audio-7B-Instruct": 0.2067713339741536, "SALMONN_7B": 0.15395706504325538, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.15924383210509452, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.13798996048275125 } }, "ytb_asr_batch1": { "wer": { "whisper_large_v3": 0.12226319428439733, "Qwen-Audio-Chat": 0.2297764461857571, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.1400092187139894, "WavLLM_fairseq": 0.41876008296842593, "Qwen2-Audio-7B-Instruct": 0.16843358684796805, "SALMONN_7B": 0.21487285856956287, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.11484981178458939, "gemini-1.5-flash": 0.1089344703080587, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.12579703464700007 } }, "mediacorp_short_test": { "wer": { "whisper_large_v3": 0.11715763436024286, "Qwen-Audio-Chat": 0.2548909377108163, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.14571621317742298, "WavLLM_fairseq": 0.2621992354396222, "Qwen2-Audio-7B-Instruct": 0.17180121430177647, "SALMONN_7B": 0.1751742747919946, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.13301101866426804, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.11434675061839443 } }, "peoples_speech_test": { "wer": { "whisper_large_v3": 0.14602420615337386, "Qwen-Audio-Chat": 0.31419144746723354, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.20140159998943682, "WavLLM_fairseq": 0.3792176325635977, "Qwen2-Audio-7B-Instruct": 0.2165498391593041, "SALMONN_7B": 0.23699946689025367, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.21050407754683692, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.14540692118393275 } }, "covost2_en_zh_test": { "bleu": { "whisper_large_v3": 0.16408986541757878, "Qwen-Audio-Chat": 15.330641138043728, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 35.274306071307024, "WavLLM_fairseq": 31.96381187282953, "Qwen2-Audio-7B-Instruct": 25.765420247070075, "SALMONN_7B": 33.88941292215531, "MERaLiON-AudioLLM-Whisper-SEA-LION": 43.941098854450516, "cascade_whisper_large_v3_llama_3_8b_instruct": 5.987143868370054 } }, "tedlium3_long_form_test": { "wer": { "whisper_large_v3": 0.03208650948413402, "Qwen-Audio-Chat": 0.2911540507002305, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.04396383619925545, "WavLLM_fairseq": 0.4536784258110264, "Qwen2-Audio-7B-Instruct": 0.08739585179932637, "SALMONN_7B": 0.14231519234178336, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.10228682857649353, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.04754476156709803 } }, "seame_dev_sge": { "wer": { "whisper_large_v3": 0.5377268970583734, "Qwen-Audio-Chat": 1.05567969634822, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.5840399155162387, "WavLLM_fairseq": 1.2204842511249197, "Qwen2-Audio-7B-Instruct": 0.5486546879304539, "SALMONN_7B": 1.0189782362484312, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.35550521901496834, "gemini-1.5-flash": 1.1100431601824359, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.507882090054792 } }, "aishell_asr_zh_test": { "wer": { "whisper_large_v3": 0.12359684029221357, "Qwen-Audio-Chat": 0.9469917443725129, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.20886539565639167, "WavLLM_fairseq": 0.7054601967888183, "Qwen2-Audio-7B-Instruct": 0.09260359129694522, "SALMONN_7B": 0.8259290055631446, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.13165449110094832, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.12450753301261111 } }, "covost2_id_en_test": { "bleu": { "whisper_large_v3": 46.01512198258627, "Qwen-Audio-Chat": 0.45648619714728844, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 46.80524126004861, "WavLLM_fairseq": 5.933522277713613, "Qwen2-Audio-7B-Instruct": 6.326113431899141, "SALMONN_7B": 26.89649039333571, "MERaLiON-AudioLLM-Whisper-SEA-LION": 44.43289180618449, "cascade_whisper_large_v3_llama_3_8b_instruct": 46.79924664837527 } }, "ytb_asr_batch2": { "wer": { "whisper_large_v3": 0.17210509244242622, "Qwen-Audio-Chat": 0.4315277327278625, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.2192622950819672, "WavLLM_fairseq": 0.48091685587631094, "Qwen2-Audio-7B-Instruct": 0.2080008649583739, "SALMONN_7B": 0.3238620391393664, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.15162720294085846, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.23561466104443723 } }, "imda_part5_30s_asr_test": { "wer": { "whisper_large_v3": 0.2143555471246589, "Qwen-Audio-Chat": 0.3016882870525747, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.22881615619208825, "WavLLM_fairseq": 0.39796588405247263, "Qwen2-Audio-7B-Instruct": 0.27856006770658537, "SALMONN_7B": 0.34868891450584405, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.17694182194919086, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.22004640235805695 } }, "parliament_short_test": { "wer": { "whisper_large_v3": 0.05543951935226013, "Qwen-Audio-Chat": 0.09347360821020603, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.07325752301384698, "WavLLM_fairseq": 0.09512390087929656, "Qwen2-Audio-7B-Instruct": 0.08416492612361723, "SALMONN_7B": 0.08676929424202573, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.056935097083623425, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.05742502771975968 } }, "idpc_test": { "wer": { "whisper_large_v3": 0.19880239520958085, "Qwen-Audio-Chat": 0.7710863986313088, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.16766467065868262, "WavLLM_fairseq": 0.7686911890504705, "Qwen2-Audio-7B-Instruct": 0.19093242087254064, "SALMONN_7B": 0.4550898203592814, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.30008554319931563, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.17741659538066723 } }, "imda_part3_30s_ds_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 16.4, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 45.4, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 31.6, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 33.8, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 9.0, "success_rate": 0.99 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 48.4, "success_rate": 0.99 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 37.400000000000006, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 47.400000000000006, "success_rate": 1.0 } } }, "cn_college_listen_mcq_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 63.232056362835756, "success_rate": 0.9995596653456627 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 91.85380889476001, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 66.31439894319684, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 74.7247908410392, "success_rate": 0.9995596653456627 }, "SALMONN_7B": { "judge_score": 50.99075297225891, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 88.50726552179657, "success_rate": 1.0 }, "gemini-1.5-flash": { "judge_score": 89.25583443416997, "success_rate": 0.9991193306913254 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 85.2928225451343, "success_rate": 1.0 } } }, "imda_part3_30s_sqa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 51.08, "success_rate": 0.998 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 70.17999999999999, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 60.620000000000005, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 50.8, "success_rate": 0.999 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 70.28, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 73.0, "success_rate": 0.999 } } }, "openhermes_audio_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 10.600000000000001, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 72.2, "success_rate": 0.96 }, "WavLLM_fairseq": { "judge_score": 19.2, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 44.800000000000004, "success_rate": 0.96 }, "SALMONN_7B": { "judge_score": 15.8, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 65.6, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 63.0, "success_rate": 0.93 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 75.0, "success_rate": 1.0 } } }, "imda_part5_30s_sqa_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 47.800000000000004, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 74.0, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 50.8, "success_rate": 0.99 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 51.6, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 44.6, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 64.80000000000001, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 57.800000000000004, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 64.80000000000001, "success_rate": 1.0 } } }, "slue_p2_sqa5_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 79.36274509803921, "success_rate": 0.9975490196078431 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 88.57843137254902, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 83.92156862745098, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 80.04901960784315, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 83.48039215686273, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 86.76470588235293, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 82.99019607843137, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 87.79411764705883, "success_rate": 1.0 } } }, "ytb_sds_batch1": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 43.878954607977995, "success_rate": 0.9917469050894085 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 64.12654745529574, "success_rate": 0.9986244841815681 }, "WavLLM_fairseq": { "judge_score": 55.625859697386524, "success_rate": 0.9917469050894085 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 51.5818431911967, "success_rate": 0.9986244841815681 }, "SALMONN_7B": { "judge_score": 31.279229711141674, "success_rate": 0.9972489683631361 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 53.97524071526823, "success_rate": 0.9944979367262724 }, "gemini-1.5-flash": { "judge_score": 65.9697386519945, "success_rate": 0.9931224209078404 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 59.44979367262724, "success_rate": 0.9972489683631361 } } }, "voxceleb_gender_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 70.5990972507181, "success_rate": 0.9997948297086582 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 34.94050061551087, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 69.61427985227739, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 99.1177677472302, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 88.79770209273697, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 99.75379565038982, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 42.921624948707425, "success_rate": 1.0 } } }, "dream_tts_mcq_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 59.749085206481965, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 89.33612127548353, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 66.5446941975954, "success_rate": 0.9984317825405122 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 66.49242028227914, "success_rate": 0.9994772608468374 }, "SALMONN_7B": { "judge_score": 56.455828541557764, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 84.31782540512285, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 86.4610559330894, "success_rate": 1.0 } } }, "ytb_sqa_batch1": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 60.827586206896555, "success_rate": 0.9980295566502463 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 70.18719211822659, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 60.70935960591133, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 60.453201970443345, "success_rate": 0.9980295566502463 }, "SALMONN_7B": { "judge_score": 55.665024630541865, "success_rate": 0.9990147783251232 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 64.51231527093596, "success_rate": 0.9980295566502463 }, "gemini-1.5-flash": { "judge_score": 78.06896551724138, "success_rate": 0.9980295566502463 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 67.3103448275862, "success_rate": 1.0 } } }, "spoken_squad_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 64.8327415436367, "success_rate": 0.9990655952158475 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 88.61894972902262, "success_rate": 0.9998131190431695 }, "WavLLM_fairseq": { "judge_score": 77.64903756307233, "success_rate": 0.997383666604373 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 64.86264249672958, "success_rate": 0.9971967856475425 }, "SALMONN_7B": { "judge_score": 66.39506634273968, "success_rate": 0.9994393571295085 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 73.66473556344609, "success_rate": 0.999252476172678 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 83.81984675761541, "success_rate": 0.998131190431695 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 90.12521024107643, "success_rate": 1.0 } } }, "imda_part4_30s_sqa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 41.92, "success_rate": 0.999 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 66.34, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 50.279999999999994, "success_rate": 0.999 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 61.980000000000004, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 64.9, "success_rate": 1.0 } } }, "imda_gr_dialogue": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 37.2, "success_rate": 0.9996666666666667 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 19.6, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 46.766666666666666, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 61.56666666666667, "success_rate": 0.9996666666666667 }, "SALMONN_7B": { "judge_score": 42.733333333333334, "success_rate": 0.9993333333333333 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 93.76666666666667, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 25.433333333333337, "success_rate": 0.9996666666666667 } } }, "imda_ar_dialogue": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 0.6666666666666667, "success_rate": 0.9996666666666667 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 7.633333333333334, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 0.23333333333333336, "success_rate": 0.9996666666666667 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 0.9666666666666667, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 0.06666666666666667, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 77.83333333333333, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 9.666666666666666, "success_rate": 0.9986666666666667 } } }, "audiocaps_test": { "meteor": { "Qwen-Audio-Chat": 0.27553015076950976, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.05796819723943051, "WavLLM_fairseq": 0.041732965094428545, "Qwen2-Audio-7B-Instruct": 0.19891712076314283, "SALMONN_7B": 0.20994052484339956, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.24920047034353812, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.07953048457785493 }, "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 47.04090909090909, "success_rate": 0.9990909090909091 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 3.0954545454545457, "success_rate": 0.9995454545454545 }, "WavLLM_fairseq": { "judge_score": 5.5, "success_rate": 0.9977272727272727 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 40.77727272727273, "success_rate": 0.9977272727272727 }, "SALMONN_7B": { "judge_score": 37.445454545454545, "success_rate": 0.9988636363636364 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 38.00454545454545, "success_rate": 0.9997727272727273 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 2.4727272727272727, "success_rate": 0.9997727272727273 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 4.868181818181818, "success_rate": 0.9981818181818182 } } }, "imda_part5_30s_ds_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 39.14, "success_rate": 0.996 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 61.48, "success_rate": 0.996 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 45.38, "success_rate": 0.997 }, "SALMONN_7B": { "judge_score": 24.340000000000003, "success_rate": 0.998 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 54.379999999999995, "success_rate": 0.998 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 63.68000000000001, "success_rate": 1.0 } } }, "ytb_pqa_batch1": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 37.16117216117216, "success_rate": 0.9990842490842491 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 55.01831501831502, "success_rate": 0.9990842490842491 }, "WavLLM_fairseq": { "judge_score": 40.95238095238095, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 36.97802197802198, "success_rate": 0.9981684981684982 }, "SALMONN_7B": { "judge_score": 32.124542124542124, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 40.97069597069597, "success_rate": 0.9990842490842491 }, "gemini-1.5-flash": { "judge_score": 49.908424908424905, "success_rate": 0.9972527472527473 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 52.252747252747255, "success_rate": 0.9990842490842491 } } }, "imda_ar_sentence": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 3.933333333333333, "success_rate": 0.9996666666666667 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 26.016666666666666, "success_rate": 0.9998333333333334 }, "WavLLM_fairseq": { "judge_score": 2.6833333333333336, "success_rate": 0.999 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 2.55, "success_rate": 0.9998333333333334 }, "SALMONN_7B": { "judge_score": 2.5166666666666666, "success_rate": 0.999 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 7.816666666666666, "success_rate": 0.9995 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 12.416666666666666, "success_rate": 0.9995 } } }, "imda_part6_30s_sqa_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 51.4, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 71.6, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 62.199999999999996, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 53.6, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 46.8, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 67.2, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 64.0, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 67.0, "success_rate": 1.0 } } }, "imda_gr_sentence": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 57.550000000000004, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 26.35, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 49.06666666666666, "success_rate": 0.9996666666666667 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 68.38333333333333, "success_rate": 0.9996666666666667 }, "SALMONN_7B": { "judge_score": 59.766666666666666, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 66.13333333333333, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 36.016666666666666, "success_rate": 1.0 } } }, "imda_part4_30s_ds_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 18.060000000000002, "success_rate": 0.994 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 43.4, "success_rate": 0.999 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 25.019999999999996, "success_rate": 0.998 }, "SALMONN_7B": { "judge_score": 9.399999999999999, "success_rate": 0.999 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 37.879999999999995, "success_rate": 0.993 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 47.74, "success_rate": 0.999 } } }, "meld_emotion_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 50.72796934865901, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 47.356321839080465, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 41.57088122605364, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 41.60919540229885, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 30.536398467432953, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 36.36015325670498, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 36.81992337164751, "success_rate": 1.0 } } }, "muchomusic_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 59.0564448188711, "success_rate": 0.9991575400168492 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 51.727042965459134, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 44.3133951137321, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 71.60909856781802, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 50.88458298230834, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 57.7927548441449, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 56.44481887110362, "success_rate": 1.0 } } }, "imda_part6_30s_ds_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 43.84, "success_rate": 0.993 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 65.6, "success_rate": 0.996 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 48.38, "success_rate": 0.999 }, "SALMONN_7B": { "judge_score": 27.12, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 59.2, "success_rate": 0.999 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 67.58, "success_rate": 1.0 } } }, "clotho_aqa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 61.934856587263, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 24.647544968400585, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 43.01199466903598, "success_rate": 0.998223011994669 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 50.919591292758774, "success_rate": 0.9991115059973346 }, "SALMONN_7B": { "judge_score": 57.75401069518716, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 63.15021876519203, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 29.47134606841404, "success_rate": 0.9991115059973346 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 28.076410484229232, "success_rate": 1.0 } } }, "imda_part3_30s_sqa_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 32.2, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 56.0, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 45.199999999999996, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 42.0, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 40.599999999999994, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 51.4, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 49.0, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 52.800000000000004, "success_rate": 1.0 } } }, "imda_part6_30s_sqa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 63.040000000000006, "success_rate": 0.998 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 83.08, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 69.42, "success_rate": 0.998 }, "SALMONN_7B": { "judge_score": 66.86, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 80.60000000000001, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 81.8, "success_rate": 0.999 } } }, "imda_30s_ds_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 31.295, "success_rate": 0.99625 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 54.515, "success_rate": 0.99575 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 38.915, "success_rate": 0.99775 }, "SALMONN_7B": { "judge_score": 18.345, "success_rate": 0.999 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 48.269999999999996, "success_rate": 0.998 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 57.99, "success_rate": 0.99975 } } }, "iemocap_emotion_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 29.382470119521916, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 44.322709163346616, "success_rate": 0.99800796812749 }, "WavLLM_fairseq": { "judge_score": 59.76095617529881, "success_rate": 0.999003984063745 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 53.98406374501992, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 23.804780876494025, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 48.505976095617534, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 46.713147410358566, "success_rate": 1.0 } } }, "imda_part6_30s_ds_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 40.4, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 65.4, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 49.400000000000006, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 46.2, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 24.2, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 62.599999999999994, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 57.199999999999996, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 64.4, "success_rate": 1.0 } } }, "imda_30s_sqa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 54.669999999999995, "success_rate": 0.99875 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 75.09, "success_rate": 0.99875 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 62.190000000000005, "success_rate": 0.99925 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 72.475, "success_rate": 0.99925 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 75.11999999999999, "success_rate": 0.9995 } } }, "wavcaps_qa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 42.69736842105263, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 18.88157894736842, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 26.25, "success_rate": 0.9967105263157895 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 44.473684210526315, "success_rate": 0.9967105263157895 }, "SALMONN_7B": { "judge_score": 47.30263157894737, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 46.31578947368421, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 16.710526315789473, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 14.736842105263158, "success_rate": 1.0 } } }, "wavcaps_test": { "meteor": { "Qwen-Audio-Chat": 0.2355106805560457, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": 0.120421856260385, "WavLLM_fairseq": 0.06399522524688675, "Qwen2-Audio-7B-Instruct": 0.21342294856199182, "SALMONN_7B": 0.17175112770658157, "MERaLiON-AudioLLM-Whisper-SEA-LION": 0.3175511907248581, "cascade_whisper_large_v3_llama_3_8b_instruct": 0.1388630786594543 }, "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 32.9364161849711, "success_rate": 0.999421965317919 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 6.3468208092485545, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 6.901734104046243, "success_rate": 0.9976878612716763 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 33.78034682080925, "success_rate": 0.9976878612716763 }, "SALMONN_7B": { "judge_score": 23.76878612716763, "success_rate": 0.999421965317919 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 33.97687861271676, "success_rate": 0.999421965317919 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 3.445086705202312, "success_rate": 0.9988439306358381 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 4.61271676300578, "success_rate": 0.999421965317919 } } }, "imda_part3_30s_ds_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 25.22, "success_rate": 0.997 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 48.339999999999996, "success_rate": 0.998 }, "WavLLM_fairseq": { "judge_score": 36.5, "success_rate": 0.997 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 35.54, "success_rate": 0.996 }, "SALMONN_7B": { "judge_score": 12.82, "success_rate": 0.998 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 42.32, "success_rate": 0.998 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 52.38, "success_rate": 1.0 } } }, "meld_sentiment_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 44.90421455938697, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 56.59003831417625, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 51.072796934865906, "success_rate": 0.9996168582375479 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 53.9463601532567, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 41.7624521072797, "success_rate": 0.9996168582375479 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 46.206896551724135, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 45.593869731800766, "success_rate": 0.9996168582375479 } } }, "imda_part5_30s_ds_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 28.2, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 58.0, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 45.199999999999996, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 40.4, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 17.2, "success_rate": 0.99 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 57.0, "success_rate": 0.99 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 49.0, "success_rate": 0.99 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 56.8, "success_rate": 1.0 } } }, "imda_part5_30s_sqa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 61.260000000000005, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 80.34, "success_rate": 0.999 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 68.52000000000001, "success_rate": 0.999 }, "SALMONN_7B": { "judge_score": 62.62, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 76.56, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 80.36, "success_rate": 1.0 } } }, "voxceleb_accent_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 48.05088223225277, "success_rate": 0.9995896594173164 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 24.640951990151827, "success_rate": 0.9997948297086582 }, "WavLLM_fairseq": { "judge_score": 39.96717275338531, "success_rate": 0.9993844891259746 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 29.187525646286417, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 34.222404595814524, "success_rate": 0.9993844891259746 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 47.01682396389003, "success_rate": 0.9997948297086582 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 39.32704144439885, "success_rate": 0.9993844891259746 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 39.462453836684446, "success_rate": 1.0 } } }, "audiocaps_qa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 50.22364217252396, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 18.466453674121407, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 29.840255591054312, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 45.75079872204473, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 50.287539936102235, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 49.77635782747604, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 17.380191693290733, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 14.63258785942492, "success_rate": 1.0 } } }, "public_sg_speech_qa_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 63.16860465116279, "success_rate": 0.9941860465116279 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 73.11046511627907, "success_rate": 0.998546511627907 }, "WavLLM_fairseq": { "judge_score": 58.54651162790698, "success_rate": 0.9825581395348837 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 58.31395348837209, "success_rate": 0.9927325581395349 }, "SALMONN_7B": { "judge_score": 59.24418604651163, "success_rate": 0.997093023255814 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 59.7093023255814, "success_rate": 0.997093023255814 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 64.94186046511628, "success_rate": 0.9927325581395349 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 73.02325581395348, "success_rate": 1.0 } } }, "imda_30s_ds_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 30.65, "success_rate": 0.995 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 50.15, "success_rate": 0.9975 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 37.599999999999994, "success_rate": 0.995 }, "SALMONN_7B": { "judge_score": 16.15, "success_rate": 0.9975 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 43.849999999999994, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 54.65, "success_rate": 1.0 } } }, "alpaca_audio_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 9.8, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 73.8, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 21.6, "success_rate": 0.99 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 52.599999999999994, "success_rate": 0.99 }, "SALMONN_7B": { "judge_score": 17.2, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 74.80000000000001, "success_rate": 0.99 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 70.8, "success_rate": 0.96 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 77.8, "success_rate": 1.0 } } }, "imda_30s_sqa_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 42.199999999999996, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 62.95, "success_rate": 0.9975 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 47.1, "success_rate": 0.995 }, "SALMONN_7B": { "judge_score": 42.300000000000004, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 55.7, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 61.550000000000004, "success_rate": 1.0 } } }, "imda_part4_30s_ds_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 16.0, "success_rate": 0.99 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 44.0, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 31.6, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 24.8, "success_rate": 0.97 }, "SALMONN_7B": { "judge_score": 7.0, "success_rate": 0.99 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 46.4, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 36.0, "success_rate": 0.99 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 48.2, "success_rate": 1.0 } } }, "imda_part4_30s_sqa_human_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 37.8, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 66.0, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 46.6, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 39.6, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 36.6, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 53.2, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 53.8, "success_rate": 1.0 } }, "gpt4o_judge": { "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 61.4, "success_rate": 1.0 } } }, "iemocap_gender_test": { "llama3_70b_judge": { "Qwen-Audio-Chat": { "judge_score": 50.0996015936255, "success_rate": 1.0 }, "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 15.737051792828685, "success_rate": 1.0 }, "WavLLM_fairseq": { "judge_score": 51.932270916334666, "success_rate": 1.0 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 92.80876494023903, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 81.31474103585658, "success_rate": 1.0 }, "MERaLiON-AudioLLM-Whisper-SEA-LION": { "judge_score": 93.48605577689243, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 44.22310756972111, "success_rate": 1.0 } } }, "imda_30s_gr_test": { "llama3_70b_judge": { "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 18.46666666666667, "success_rate": 1.0 } } }, "imda_30s_ar_test": { "llama3_70b_judge": { "cascade_whisper_large_v2_gemma2_9b_cpt_sea_lionv3_instruct": { "judge_score": 15.773333333333333, "success_rate": 0.9996666666666667 }, "Qwen2-Audio-7B-Instruct": { "judge_score": 5.106666666666667, "success_rate": 1.0 }, "SALMONN_7B": { "judge_score": 5.673333333333334, "success_rate": 1.0 }, "cascade_whisper_large_v3_llama_3_8b_instruct": { "judge_score": 27.186666666666667, "success_rate": 0.9996666666666667 } } }, "mmau_mini": { "llama3_70b_judge": { "phi_4_multimodal_instruct": { "judge_score": 59.4, "success_rate": 1.0 } } }, "nlb_asr_test": { "wer": { "cascade_whisper_large_v3_llama_3_8b_instruct": 0.2796380263880551 } } }