Hugging Face's logo

speechbrain
/
tts-hifigan-libritts-16kHz

Text-to-Speech speechbrain
English Vocoder HiFIGAN TTS speech-synthesis
Model card Files Community
2
speechbrainteam commited on
Commit
4d32c6f
•
1 Parent(s): 7135ee3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -40,7 +40,7 @@ Please notice that we encourage you to read our tutorials and learn more about
40
  ```python
41
  import torch
42
  from speechbrain.inference.vocoders import HIFIGAN
43
- hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-libritts-16kHz", savedir="tmpdir")
44
  mel_specs = torch.rand(2, 80,298)
45
 
46
  # Running Vocoder (spectrogram-to-waveform)
@@ -54,7 +54,7 @@ from speechbrain.inference.vocoders import HIFIGAN
54
  from speechbrain.lobes.models.FastSpeech2 import mel_spectogram
55
 
56
  # Load a pretrained HIFIGAN Vocoder
57
- hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-libritts-16kHz", savedir="vocoder_16khz")
58
 
59
  # Load an audio file (an example file can be found in this repository)
60
  # Ensure that the audio signal is sampled at 16000 Hz; refer to the provided link for a 22050 Hz Vocoder.
40
  ```python
41
  import torch
42
  from speechbrain.inference.vocoders import HIFIGAN
43
+ hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-libritts-16kHz", savedir="pretrained_models/tts-hifigan-libritts-16kHz")
44
  mel_specs = torch.rand(2, 80,298)
45
 
46
  # Running Vocoder (spectrogram-to-waveform)
54
  from speechbrain.lobes.models.FastSpeech2 import mel_spectogram
55
 
56
  # Load a pretrained HIFIGAN Vocoder
57
+ hifi_gan = HIFIGAN.from_hparams(source="speechbrain/tts-hifigan-libritts-16kHz", savedir="pretrained_models/tts-hifigan-libritts-16kHz")
58
 
59
  # Load an audio file (an example file can be found in this repository)
60
  # Ensure that the audio signal is sampled at 16000 Hz; refer to the provided link for a 22050 Hz Vocoder.