Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
English
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-medium.en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-medium.en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-medium.en")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-medium.en") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-medium.en") - Notebooks
- Google Colab
- Kaggle
Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'.
#16
by patrickvonplaten - opened
- generation_config.json +2 -1
generation_config.json
CHANGED
|
@@ -87,10 +87,11 @@
|
|
| 87 |
]
|
| 88 |
],
|
| 89 |
"is_multilingual": false,
|
| 90 |
-
"max_initial_timestamp_index":
|
| 91 |
"max_length": 448,
|
| 92 |
"no_timestamps_token_id": 50362,
|
| 93 |
"pad_token_id": 50256,
|
|
|
|
| 94 |
"return_timestamps": false,
|
| 95 |
"suppress_tokens": [
|
| 96 |
1,
|
|
|
|
| 87 |
]
|
| 88 |
],
|
| 89 |
"is_multilingual": false,
|
| 90 |
+
"max_initial_timestamp_index": 50,
|
| 91 |
"max_length": 448,
|
| 92 |
"no_timestamps_token_id": 50362,
|
| 93 |
"pad_token_id": 50256,
|
| 94 |
+
"prev_sot_token_id": 50360,
|
| 95 |
"return_timestamps": false,
|
| 96 |
"suppress_tokens": [
|
| 97 |
1,
|