Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
English
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-small.en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-small.en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-small.en")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-small.en") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-small.en") - Notebooks
- Google Colab
- Kaggle
Commit ·
48b9de7
1
Parent(s): 287fee8
Update config.json to suppress task tokens (#8)
Browse files- Update config.json to suppress task tokens (35dc2f85ec84269888aecd97bf0cbe7b12d258ed)
Co-authored-by: Guillaume Klein <guillaumekln@users.noreply.huggingface.co>
- config.json +2 -0
config.json
CHANGED
|
@@ -125,6 +125,8 @@
|
|
| 125 |
47282,
|
| 126 |
49146,
|
| 127 |
50257,
|
|
|
|
|
|
|
| 128 |
50359,
|
| 129 |
50360,
|
| 130 |
50361
|
|
|
|
| 125 |
47282,
|
| 126 |
49146,
|
| 127 |
50257,
|
| 128 |
+
50357,
|
| 129 |
+
50358,
|
| 130 |
50359,
|
| 131 |
50360,
|
| 132 |
50361
|