Update README.md
Browse files
README.md
CHANGED
|
@@ -14,6 +14,10 @@ tags:
|
|
| 14 |
# Fine-tuned facebook/wav2vec2-base large model for speech recognition in English
|
| 15 |
|
| 16 |
Fine-tuned [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on English using the train and validation splits of [zodata](https://www.kaggle.com/datasets/mohamedk0emad/zodata).
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 18 |
|
| 19 |
This model has been fine-tuned thanks to the GPU credits given by the [kaggle](https://www.kaggle.com/)
|
|
|
|
| 14 |
# Fine-tuned facebook/wav2vec2-base large model for speech recognition in English
|
| 15 |
|
| 16 |
Fine-tuned [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on English using the train and validation splits of [zodata](https://www.kaggle.com/datasets/mohamedk0emad/zodata).
|
| 17 |
+
the dataset has 307912 transcibed voice samples, we used 6158 samples for training and 6036 samples for testing
|
| 18 |
+
and the result for testing with WER accuracy metric is:
|
| 19 |
+
Test WER: 0.340
|
| 20 |
+
|
| 21 |
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 22 |
|
| 23 |
This model has been fine-tuned thanks to the GPU credits given by the [kaggle](https://www.kaggle.com/)
|