Automatic Speech Recognition
Transformers
Safetensors
English
whisper
FP8
vllm
audio
compressed-tensors
Instructions to use RedHatAI/whisper-tiny-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/whisper-tiny-FP8-Dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="RedHatAI/whisper-tiny-FP8-Dynamic")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("RedHatAI/whisper-tiny-FP8-Dynamic") model = AutoModelForSpeechSeq2Seq.from_pretrained("RedHatAI/whisper-tiny-FP8-Dynamic", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -191,21 +191,21 @@ lmms-eval \
|
|
| 191 |
<tr>
|
| 192 |
<td rowspan="3"><b>Fleurs (X→en, BLEU)</b></td>
|
| 193 |
<td>cmn_hans_cn</td>
|
| 194 |
-
<td></td>
|
| 195 |
-
<td></td>
|
| 196 |
-
<td></td>
|
| 197 |
</tr>
|
| 198 |
<tr>
|
| 199 |
<td>en</td>
|
| 200 |
-
<td></td>
|
| 201 |
-
<td></td>
|
| 202 |
-
<td></td>
|
| 203 |
</tr>
|
| 204 |
<tr>
|
| 205 |
<td>yue_hant_hk</td>
|
| 206 |
-
<td></td>
|
| 207 |
-
<td></td>
|
| 208 |
-
<td></td>
|
| 209 |
</tr>
|
| 210 |
</tbody>
|
| 211 |
</table>
|
|
|
|
| 191 |
<tr>
|
| 192 |
<td rowspan="3"><b>Fleurs (X→en, BLEU)</b></td>
|
| 193 |
<td>cmn_hans_cn</td>
|
| 194 |
+
<td>43.8226</td>
|
| 195 |
+
<td>45.0539</td>
|
| 196 |
+
<td>97.27%</td>
|
| 197 |
</tr>
|
| 198 |
<tr>
|
| 199 |
<td>en</td>
|
| 200 |
+
<td>13.6638</td>
|
| 201 |
+
<td>15.2980</td>
|
| 202 |
+
<td>89.32%</td>
|
| 203 |
</tr>
|
| 204 |
<tr>
|
| 205 |
<td>yue_hant_hk</td>
|
| 206 |
+
<td>60.1848</td>
|
| 207 |
+
<td>67.5437</td>
|
| 208 |
+
<td>89.10%</td>
|
| 209 |
</tr>
|
| 210 |
</tbody>
|
| 211 |
</table>
|