Upload folder using huggingface_hub
Browse files- app/content.py +7 -7
app/content.py
CHANGED
@@ -142,22 +142,22 @@ dataset_diaplay_information = {
|
|
142 |
'UKUS-News-Short' : 'Under Development',
|
143 |
'Mediacorp-Short' : 'Under Development',
|
144 |
|
145 |
-
'YouTube ASR: English Singapore Content' : 'YouTube Evaluation Dataset for ASR Task: <br> This dataset contains English and Singlish audio clips, featuring Singapore-related content.
|
146 |
|
147 |
-
'YouTube ASR: English with Strong Emotion' : 'YouTube Evaluation Dataset for ASR Task:
|
148 |
|
149 |
-
'YouTube ASR: Malay English Prompt': 'YouTube Evaluation Dataset for ASR Task:
|
150 |
|
151 |
-
'YouTube ASR: Malay with Malay Prompt': 'YouTube Evaluation Dataset for ASR Task:
|
152 |
|
153 |
'SEAME-Dev-Mandarin' : 'Under Development',
|
154 |
'SEAME-Dev-Singlish' : 'Under Development',
|
155 |
|
156 |
-
'YouTube SQA: English with Singapore Content': 'YouTube Evaluation Dataset for Speech-QA Task:
|
157 |
|
158 |
-
'YouTube SDS: English with Singapore Content': 'YouTube Evaluation Dataset for Summary Task:
|
159 |
|
160 |
-
'YouTube PQA: English with Singapore Content': 'YouTube Evaluation Dataset for Paralinguistics Task:
|
161 |
|
162 |
|
163 |
}
|
|
|
142 |
'UKUS-News-Short' : 'Under Development',
|
143 |
'Mediacorp-Short' : 'Under Development',
|
144 |
|
145 |
+
'YouTube ASR: English Singapore Content' : 'YouTube Evaluation Dataset for ASR Task: <br> This dataset contains English and Singlish audio clips, featuring Singapore-related content. <br> It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.',
|
146 |
|
147 |
+
'YouTube ASR: English with Strong Emotion' : 'YouTube Evaluation Dataset for ASR Task: <br> This dataset contains English and some unknown languages audio clips, featuring speech with strong emotional expression. <br> It includes approximately 3.9 hours of audio, with each clip lasting 30 seconds.',
|
148 |
|
149 |
+
'YouTube ASR: Malay English Prompt': 'YouTube Evaluation Dataset for ASR Task: <br> This dataset mainly contains Malay and some English audio clips, featuring with English prompts. <br> It includes approximately 2.55 hours of audio, with indicidual clips ranging form 30 seconds to 95 seconds in length.',
|
150 |
|
151 |
+
'YouTube ASR: Malay with Malay Prompt': 'YouTube Evaluation Dataset for ASR Task: <br> This dataset use the same audio from <i>YouTube ASR: Malay English Prompt</i>, except featuring with Malay prompts. <br> It includes approximately 2.55 hours of audio, with indicidual clips ranging form 30 seconds to 95 seconds in length.',
|
152 |
|
153 |
'SEAME-Dev-Mandarin' : 'Under Development',
|
154 |
'SEAME-Dev-Singlish' : 'Under Development',
|
155 |
|
156 |
+
'YouTube SQA: English with Singapore Content': 'YouTube Evaluation Dataset for Speech-QA Task: <br> This dataset use the same audio from <i>YouTube ASR: English Singapore Content</i>, featuring Singapore-related content. <br> It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.',
|
157 |
|
158 |
+
'YouTube SDS: English with Singapore Content': 'YouTube Evaluation Dataset for Summary Task: <br> This dataset use the same audio from <i>YouTube ASR: English Singapore Content</i>, featuring Singapore-related content. <br> It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.',
|
159 |
|
160 |
+
'YouTube PQA: English with Singapore Content': 'YouTube Evaluation Dataset for Paralinguistics Task: <br> This dataset use the same audio from <i>YouTube ASR: English Singapore Content</i>, featuring Singapore-related content. <br> It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.',
|
161 |
|
162 |
|
163 |
}
|