Update README.md
Browse files
README.md
CHANGED
@@ -34,17 +34,37 @@ Please notice that we encourage you to read our tutorials and learn more about
|
|
34 |
[SpeechBrain](https://speechbrain.github.io).
|
35 |
|
36 |
|
37 |
-
###
|
38 |
|
39 |
```python
|
40 |
from speechbrain.pretrained import UnitHIFIGAN
|
41 |
|
42 |
-
hifi_gan_unit = UnitHIFIGAN.from_hparams(source="speechbrain/hifigan-unit-hubert-l6-k100-ljspeech")
|
43 |
codes = torch.randint(0, 99, (100,))
|
44 |
waveform = hifi_gan.decode_unit(codes)
|
45 |
|
46 |
```
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
### Inference on GPU
|
49 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
50 |
|
|
|
34 |
[SpeechBrain](https://speechbrain.github.io).
|
35 |
|
36 |
|
37 |
+
### Using the Vocoder
|
38 |
|
39 |
```python
|
40 |
from speechbrain.pretrained import UnitHIFIGAN
|
41 |
|
42 |
+
hifi_gan_unit = UnitHIFIGAN.from_hparams(source="speechbrain/tts-hifigan-unit-hubert-l6-k100-ljspeech", savedir=tmpdir_vocoder)
|
43 |
codes = torch.randint(0, 99, (100,))
|
44 |
waveform = hifi_gan.decode_unit(codes)
|
45 |
|
46 |
```
|
47 |
|
48 |
+
### Using the Vocoder with the S2UT
|
49 |
+
```python
|
50 |
+
import torchaudio
|
51 |
+
from speechbrain.pretrained import EncoderDecoderS2UT
|
52 |
+
from speechbrain.pretrained import UnitHIFIGAN
|
53 |
+
|
54 |
+
# Intialize S2UT (Transformer) and Vocoder (HiFIGAN Unit)
|
55 |
+
s2ut = EncoderDecoderS2UT.from_hparams(source="speechbrain/s2st-transformer-fr-en-hubert-l6-k100-cvss", savedir=tmpdir_s2ut)
|
56 |
+
hifi_gan_unit = UnitHIFIGAN.from_hparams(source="speechbrain/tts-hifigan-unit-hubert-l6-k100-ljspeech", savedir=tmpdir_vocoder)
|
57 |
+
|
58 |
+
# Running the S2UT model
|
59 |
+
codes = s2ut.translate_file("speechbrain/s2st-transformer-fr-en-hubert-l6-k100-cvss/example-fr.wav")
|
60 |
+
|
61 |
+
# Running Vocoder (units-to-waveform)
|
62 |
+
waveforms = hifi_gan.decode_unit(codes)
|
63 |
+
|
64 |
+
# Save the waverform
|
65 |
+
torchaudio.save('example_TTS.wav',waveforms.squeeze(1), 16000)
|
66 |
+
```
|
67 |
+
|
68 |
### Inference on GPU
|
69 |
To perform inference on the GPU, add `run_opts={"device":"cuda"}` when calling the `from_hparams` method.
|
70 |
|