From 14c80dd1fd665ea348ce83f2b34392485ac5dfa6 Mon Sep 17 00:00:00 2001 From: Khalid Bashir Date: Sun, 19 Mar 2023 04:22:04 +0500 Subject: [PATCH] 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. ``` --- TTS/tts/models/vits.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/TTS/tts/models/vits.py b/TTS/tts/models/vits.py index 7500da61..f91115be 100644 --- a/TTS/tts/models/vits.py +++ b/TTS/tts/models/vits.py @@ -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)