update data prep and inference notebook
Browse files
README.md
CHANGED
|
@@ -28,6 +28,10 @@ model-index:
|
|
| 28 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) Bengali using a subset of 40,000 utterances from [Bengali ASR training data set containing ~196K utterances](https://www.openslr.org/53/). Tested WER using ~4200 held out from training.
|
| 29 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 30 |
Train Script can be Found at : train.py
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
## Usage
|
| 32 |
|
| 33 |
The model can be used directly (without a language model) as follows:
|
|
|
|
| 28 |
Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) Bengali using a subset of 40,000 utterances from [Bengali ASR training data set containing ~196K utterances](https://www.openslr.org/53/). Tested WER using ~4200 held out from training.
|
| 29 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 30 |
Train Script can be Found at : train.py
|
| 31 |
+
|
| 32 |
+
Data Prep Notebook : https://colab.research.google.com/drive/1JMlZPU-DrezXjZ2t7sOVqn7CJjZhdK2q?usp=sharing
|
| 33 |
+
Inference Notebook : https://colab.research.google.com/drive/1uKC2cK9JfUPDTUHbrNdOYqKtNozhxqgZ?usp=sharing
|
| 34 |
+
|
| 35 |
## Usage
|
| 36 |
|
| 37 |
The model can be used directly (without a language model) as follows:
|