Automatic Speech Recognition
Transformers
Safetensors
English
whisper
w8a8
INT8
vllm
audio
8-bit precision
compressed-tensors
Instructions to use RedHatAI/whisper-tiny-quantized.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RedHatAI/whisper-tiny-quantized.w8a8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="RedHatAI/whisper-tiny-quantized.w8a8")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("RedHatAI/whisper-tiny-quantized.w8a8") model = AutoModelForSpeechSeq2Seq.from_pretrained("RedHatAI/whisper-tiny-quantized.w8a8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -256,7 +256,7 @@ lmms-eval \
|
|
| 256 |
<td>98.74%</td>
|
| 257 |
</tr>
|
| 258 |
<tr>
|
| 259 |
-
<td rowspan="3"><b>Fleurs (X→en,
|
| 260 |
<td>cmn_hans_cn</td>
|
| 261 |
<td>43.8226</td>
|
| 262 |
<td>43.6435</td>
|
|
|
|
| 256 |
<td>98.74%</td>
|
| 257 |
</tr>
|
| 258 |
<tr>
|
| 259 |
+
<td rowspan="3"><b>Fleurs (X→en, WER)</b></td>
|
| 260 |
<td>cmn_hans_cn</td>
|
| 261 |
<td>43.8226</td>
|
| 262 |
<td>43.6435</td>
|