Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
English
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use openai/whisper-tiny.en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-tiny.en with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-tiny.en")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-tiny.en") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-tiny.en") - Notebooks
- Google Colab
- Kaggle
Update generation config with word-level alignment heads
#16
by sanchit-gandhi - opened
- generation_config.json +35 -1
generation_config.json
CHANGED
|
@@ -1,4 +1,38 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"begin_suppress_tokens": [
|
| 3 |
220,
|
| 4 |
50256
|
|
@@ -110,5 +144,5 @@
|
|
| 110 |
50360,
|
| 111 |
50361
|
| 112 |
],
|
| 113 |
-
"transformers_version": "4.
|
| 114 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
1,
|
| 5 |
+
0
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
2,
|
| 9 |
+
0
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
2,
|
| 13 |
+
5
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
3,
|
| 17 |
+
0
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
3,
|
| 21 |
+
1
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
3,
|
| 25 |
+
2
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
3,
|
| 29 |
+
3
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
3,
|
| 33 |
+
4
|
| 34 |
+
]
|
| 35 |
+
],
|
| 36 |
"begin_suppress_tokens": [
|
| 37 |
220,
|
| 38 |
50256
|
|
|
|
| 144 |
50360,
|
| 145 |
50361
|
| 146 |
],
|
| 147 |
+
"transformers_version": "4.31.0.dev0"
|
| 148 |
}
|