Automatic Speech Recognition
Transformers
Safetensors
English
whisper
FP8
vllm
audio
compressed-tensors
Instructions to use RedHatAI/whisper-large-v2-FP8-Dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/whisper-large-v2-FP8-Dynamic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="RedHatAI/whisper-large-v2-FP8-Dynamic")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("RedHatAI/whisper-large-v2-FP8-Dynamic") model = AutoModelForSpeechSeq2Seq.from_pretrained("RedHatAI/whisper-large-v2-FP8-Dynamic") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -189,7 +189,7 @@ lmms-eval \
|
|
| 189 |
<td>101.06%</td>
|
| 190 |
</tr>
|
| 191 |
<tr>
|
| 192 |
-
<td rowspan="3"><b>Fleurs (X→en,
|
| 193 |
<td>cmn_hans_cn</td>
|
| 194 |
<td>15.2148</td>
|
| 195 |
<td>14.7614</td>
|
|
|
|
| 189 |
<td>101.06%</td>
|
| 190 |
</tr>
|
| 191 |
<tr>
|
| 192 |
+
<td rowspan="3"><b>Fleurs (X→en, WER)</b></td>
|
| 193 |
<td>cmn_hans_cn</td>
|
| 194 |
<td>15.2148</td>
|
| 195 |
<td>14.7614</td>
|