tuna2134/sbv2-v2
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Update data_utils.py

Browse Source
This commit is contained in:
Stardust·减
2023-08-21 07:23:06 +08:00
committed by GitHub
parent 7cffaf2f08
commit d2ac51c8c2
1 changed files with 21 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
data_utils.py
View File

@@ -83,12 +83,28 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
audio_norm = audio / self.max_wav_value
audio_norm = audio_norm.unsqueeze(0)
spec_filename = filename.replace(".wav", ".spec.pt")
try:
if self.use_mel_spec_posterior:
spec_filename = spec_filename.replace(".spec.pt", ".mel.pt")
if os.path.exists(spec_filename):
spec = torch.load(spec_filename)
except:
spec = spectrogram_torch(audio_norm, self.filter_length,
self.sampling_rate, self.hop_length, self.win_length,
center=False)
else:
if self.use_mel_spec_posterior:
''' TODO : (need verification)
if linear spec exists convert to
mel from existing linear spec (uncomment below lines) '''
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)
else:
spec = spectrogram_torch(audio_norm, self.filter_length,
self.sampling_rate, self.hop_length, self.win_length,
center=False)
spec = torch.squeeze(spec, 0)
torch.save(spec, spec_filename)
return spec, audio_norm