Automatic Speech Recognition
Transformers
PyTorch
JAX
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use danurahul/wav2vec2-large-xlsr-pa-IN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use danurahul/wav2vec2-large-xlsr-pa-IN with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="danurahul/wav2vec2-large-xlsr-pa-IN")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN") model = AutoModelForCTC.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -88,7 +88,7 @@ model = Wav2Vec2ForCTC.from_pretrained("danurahul/wav2vec2-large-xlsr-pa-IN")
|
|
| 88 |
|
| 89 |
model.to("cuda")
|
| 90 |
|
| 91 |
-
chars_to_ignore_regex = '[\\\\\\\\,\\\\\\\\?\\\\\\\\.\\\\\\\\!\\\\\\\\-\\\\\\\\;\\\\\\\\:\\\\\\\\"\\\\\\\\“\\\\\\\\%\\\\\\\\‘\\\\\\\\”\\\\\\\\�]'
|
| 92 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 93 |
|
| 94 |
# Preprocessing the datasets.
|
|
@@ -118,7 +118,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
|
|
| 118 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
| 119 |
```
|
| 120 |
|
| 121 |
-
**Test Result**:
|
| 122 |
|
| 123 |
|
| 124 |
## Training
|
|
|
|
| 88 |
|
| 89 |
model.to("cuda")
|
| 90 |
|
| 91 |
+
chars_to_ignore_regex = '[\\\\\\\\\\\\\\\\,\\\\\\\\\\\\\\\\?\\\\\\\\\\\\\\\\.\\\\\\\\\\\\\\\\!\\\\\\\\\\\\\\\\-\\\\\\\\\\\\\\\\;\\\\\\\\\\\\\\\\:\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\“\\\\\\\\\\\\\\\\%\\\\\\\\\\\\\\\\‘\\\\\\\\\\\\\\\\”\\\\\\\\\\\\\\\\�]'
|
| 92 |
resampler = torchaudio.transforms.Resample(48_000, 16_000)
|
| 93 |
|
| 94 |
# Preprocessing the datasets.
|
|
|
|
| 118 |
print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
|
| 119 |
```
|
| 120 |
|
| 121 |
+
**Test Result**: 100 %
|
| 122 |
|
| 123 |
|
| 124 |
## Training
|