Update README.md
Browse files
README.md
CHANGED
|
@@ -64,7 +64,11 @@ transcription = processor.batch_decode(logits.numpy()).text
|
|
| 64 |
print("Prediction:",transcription[0])
|
| 65 |
```
|
| 66 |
|
| 67 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
1- <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/645098004f731658826cfe57/tZLR9sn6VnsjYS5xT2qFB.wav"></audio>
|
| 69 |
|
| 70 |
2- <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/645098004f731658826cfe57/_6p54hi5JRt_PIqxY-P0I.wav"></audio>
|
|
|
|
| 64 |
print("Prediction:",transcription[0])
|
| 65 |
```
|
| 66 |
|
| 67 |
+
You can try the model with live recording using this Google Colab notebook : [Live Recording Recognition](https://colab.research.google.com/drive/1WYFG03o93-CBFNHhAuAo3MNmzgo4nLEJ?usp=sharing)
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
sample audios and Outputs
|
| 71 |
+
|
| 72 |
1- <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/645098004f731658826cfe57/tZLR9sn6VnsjYS5xT2qFB.wav"></audio>
|
| 73 |
|
| 74 |
2- <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/645098004f731658826cfe57/_6p54hi5JRt_PIqxY-P0I.wav"></audio>
|