Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-tiny")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-tiny") - Notebooks
- Google Colab
- Kaggle
Commit ·
7e5a814
1
Parent(s): be0ba7c
Correct forced decoder ids
Browse files@sanchit-gandhi
Any reason why the generation config doesn't match the config here: https://huggingface.co/openai/whisper-tiny/blob/be0ba7c2f24f0127b27863a23a08002af4c2c279/config.json#L26
- generation_config.json +5 -1
generation_config.json
CHANGED
|
@@ -35,11 +35,15 @@
|
|
| 35 |
"forced_decoder_ids": [
|
| 36 |
[
|
| 37 |
1,
|
| 38 |
-
|
| 39 |
],
|
| 40 |
[
|
| 41 |
2,
|
| 42 |
50359
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
]
|
| 44 |
],
|
| 45 |
"is_multilingual": true,
|
|
|
|
| 35 |
"forced_decoder_ids": [
|
| 36 |
[
|
| 37 |
1,
|
| 38 |
+
50259
|
| 39 |
],
|
| 40 |
[
|
| 41 |
2,
|
| 42 |
50359
|
| 43 |
+
],
|
| 44 |
+
[
|
| 45 |
+
3,
|
| 46 |
+
50363
|
| 47 |
]
|
| 48 |
],
|
| 49 |
"is_multilingual": true,
|