diff --git a/data_utils.py b/data_utils.py index 19f098c..be3a29a 100644 --- a/data_utils.py +++ b/data_utils.py @@ -93,12 +93,6 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset): spec = torch.load(spec_filename) except: if self.use_mel_spec_posterior: - # if os.path.exists(filename.replace(".wav", ".spec.pt")): - # # spec, n_fft, num_mels, sampling_rate, fmin, fmax - # spec = spec_to_mel_torch( - # torch.load(filename.replace(".wav", ".spec.pt")), - # self.filter_length, self.n_mel_channels, self.sampling_rate, - # self.hparams.mel_fmin, self.hparams.mel_fmax) spec = mel_spectrogram_torch(audio_norm, self.filter_length, self.n_mel_channels, self.sampling_rate, self.hop_length, self.win_length, self.hparams.mel_fmin, self.hparams.mel_fmax, center=False) @@ -111,7 +105,6 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset): return spec, audio_norm def get_text(self, text, word2ph, phone, tone, language_str, wav_path): - # print(text, word2ph,phone, tone, language_str) pold = phone w2pho = [i for i in word2ph] word2ph = [i for i in word2ph]