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
2023-09-05 01:04:10 +08:00
committed by GitHub
parent 4127f7d00a
commit d74fe531e9
1 changed files with 0 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
data_utils.py
View File

@@ -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]
@@ -136,7 +129,6 @@ class TextAudioSpeakerLoader(torch.utils.data.Dataset):
except:
bert = get_bert(text, word2ph, language_str)
torch.save(bert, bert_path)
#print(bert.shape[-1], bert_path, text, pold)
assert bert.shape[-1] == len(phone)
assert bert.shape[-1] == len(phone), (