Upload folder using huggingface_hub
Browse files- app/content.py +6 -18
app/content.py
CHANGED
@@ -144,32 +144,20 @@ dataset_diaplay_information = {
|
|
144 |
|
145 |
'YouTube ASR: English Singapore Content' : 'YouTube Evaluation Dataset for ASR Task: \n This dataset contains English and Singlish audio clips, featuring Singapore-related content. \n 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' : '
|
148 |
-
This dataset contains English and some unknown languages audio clips, featuring speech with strong emotional expression. \n
|
149 |
-
It includes approximately 3.9 hours of audio, with each clip lasting 30 seconds.''',
|
150 |
|
151 |
-
'YouTube ASR: Malay English Prompt': '
|
152 |
-
This dataset mainly contains Malay and some English audio clips, featuring with English prompts. \n
|
153 |
-
It includes approximately 2.55 hours of audio, with indicidual clips ranging form 30 seconds to 95 seconds in length.''',
|
154 |
|
155 |
-
'YouTube ASR: Malay with Malay Prompt': '
|
156 |
-
This dataset use the same audio from *YouTube ASR: Malay English Prompt*, except featuring with Malay prompts. \n
|
157 |
-
It includes approximately 2.55 hours of audio, with indicidual clips ranging form 30 seconds to 95 seconds in length.''',
|
158 |
|
159 |
'SEAME-Dev-Mandarin' : 'Under Development',
|
160 |
'SEAME-Dev-Singlish' : 'Under Development',
|
161 |
|
162 |
-
'YouTube SQA: English with Singapore Content': '
|
163 |
-
This dataset use the same audio from *YouTube ASR: English Singapore Content*, featuring Singapore-related content. \n
|
164 |
-
It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.''',
|
165 |
|
166 |
-
'YouTube SDS: English with Singapore Content': '
|
167 |
-
This dataset use the same audio from *YouTube ASR: English Singapore Content*, featuring Singapore-related content. \n
|
168 |
-
It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.''',
|
169 |
|
170 |
-
'YouTube PQA: English with Singapore Content': '
|
171 |
-
This dataset use the same audio from *YouTube ASR: English Singapore Content*, featuring Singapore-related content. \n
|
172 |
-
It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.''',
|
173 |
|
174 |
|
175 |
}
|
|
|
144 |
|
145 |
'YouTube ASR: English Singapore Content' : 'YouTube Evaluation Dataset for ASR Task: \n This dataset contains English and Singlish audio clips, featuring Singapore-related content. \n 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: \n This dataset contains English and some unknown languages audio clips, featuring speech with strong emotional expression. \n 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: \n This dataset mainly contains Malay and some English audio clips, featuring with English prompts. \n 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: \n This dataset use the same audio from *YouTube ASR: Malay English Prompt*, except featuring with Malay prompts. \n 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: \n This dataset use the same audio from *YouTube ASR: English Singapore Content*, featuring Singapore-related content. \n 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: \n This dataset use the same audio from *YouTube ASR: English Singapore Content*, featuring Singapore-related content. \n 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: \n This dataset use the same audio from *YouTube ASR: English Singapore Content*, featuring Singapore-related content. \n It includes approximately 2.5 hours of audio, with individual clips ranging from 2 seconds to 30 seconds in length.',
|
|
|
|
|
161 |
|
162 |
|
163 |
}
|