Update README.md
Browse files
README.md
CHANGED
@@ -63,6 +63,8 @@ classifier = EncoderClassifier.from_hparams(source="speechbrain/urbansound8k_eca
|
|
63 |
out_prob, score, index, text_lab = classifier.classify_file('speechbrain/urbansound8k_ecapa/dog_bark.wav')
|
64 |
print(text_lab)
|
65 |
```
|
|
|
|
|
66 |
|
67 |
### Inference on GPU
|
68 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
|
|
63 |
out_prob, score, index, text_lab = classifier.classify_file('speechbrain/urbansound8k_ecapa/dog_bark.wav')
|
64 |
print(text_lab)
|
65 |
```
|
66 |
+
The system is trained with recordings sampled at 16kHz (single channel).
|
67 |
+
The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling *classify_file* if needed. Make sure your input tensor is compliant with the expected sampling rate if you use *encode_batch* and *classify_batch*.
|
68 |
|
69 |
### Inference on GPU
|
70 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|