Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

vits.py training fixed due to return_complex (#2418) 

Torch set default value for `return_complex=True` for `torch.stft` method
This turned warning into error:-
```
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1591, in fit
    self._fit()
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1544, in _fit
    self.train_epoch()
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1309, in train_epoch
    _, _ = self.train_step(batch, batch_num_steps, cur_step, loader_start_time)
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1162, in train_step
    outputs, loss_dict_new, step_time = self._optimize(
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 1023, in _optimize
    outputs, loss_dict = self._model_train_step(batch, model, criterion, optimizer_idx=optimizer_idx)
  File "/usr/local/lib/python3.10/dist-packages/trainer/trainer.py", line 970, in _model_train_step
    return model.train_step(*input_args)
  File "/workspace/coqui-tts/TTS/tts/models/vits.py", line 1293, in train_step
    mel_slice_hat = wav_to_mel(
  File "/workspace/coqui-tts/TTS/tts/models/vits.py", line 191, in wav_to_mel
    spec = torch.stft(
  File "/usr/local/lib/python3.10/dist-packages/torch/functional.py", line 641, in stft
    return _VF.stft(input, n_fft, hop_length, win_length, window,  # type: ignore[attr-defined]
RuntimeError: stft requires the return_complex parameter be given for real inputs, and will further require that return_complex=True in a future PyTorch release.
```
This commit is contained in:
Khalid Bashir 2023-03-19 04:22:04 +05:00 committed by GitHub
parent 12f3365185
commit 14c80dd1fd
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/models/vits.py
View File

@ -130,6 +130,7 @@ def wav_to_spec(y, n_fft, hop_length, win_length, center=False):
pad_mode="reflect",
normalized=False,
onesided=True,
return_complex=False,
)
spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)
@ -197,6 +198,7 @@ def wav_to_mel(y, n_fft, num_mels, sample_rate, hop_length, win_length, fmin, fm
pad_mode="reflect",
normalized=False,
onesided=True,
return_complex=False,
)
spec = torch.sqrt(spec.pow(2).sum(-1) + 1e-6)