Update README.md
Browse files
README.md
CHANGED
@@ -97,7 +97,7 @@ VAD.save_boundaries(boundaries)
|
|
97 |
The output is a tensor that contains the beginning/end second of each
|
98 |
detected speech segment. You can save the boundaries on a file with:
|
99 |
|
100 |
-
```
|
101 |
VAD.save_boundaries(boundaries, save_path='VAD_file.txt')
|
102 |
```
|
103 |
|
@@ -105,7 +105,7 @@ Sometimes it is useful to jointly visualize the VAD output with the input signal
|
|
105 |
|
106 |
To do it:
|
107 |
|
108 |
-
```
|
109 |
import torchaudio
|
110 |
upsampled_boundaries = VAD.upsample_boundaries(boundaries, 'pretrained_model_checkpoints/example_vad.wav')
|
111 |
torchaudio.save('vad_final.wav', upsampled_boundaries.cpu(), 16000)
|
|
|
97 |
The output is a tensor that contains the beginning/end second of each
|
98 |
detected speech segment. You can save the boundaries on a file with:
|
99 |
|
100 |
+
```
|
101 |
VAD.save_boundaries(boundaries, save_path='VAD_file.txt')
|
102 |
```
|
103 |
|
|
|
105 |
|
106 |
To do it:
|
107 |
|
108 |
+
```
|
109 |
import torchaudio
|
110 |
upsampled_boundaries = VAD.upsample_boundaries(boundaries, 'pretrained_model_checkpoints/example_vad.wav')
|
111 |
torchaudio.save('vad_final.wav', upsampled_boundaries.cpu(), 16000)
|