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

no cached mel/linear anymore

This commit is contained in:
Thomas Werkmeister 2019-04-29 11:26:01 +02:00
parent 7b2804cc0d
commit f9c6cde17f
1 changed files with 4 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
datasets/TTSDataset.py
View File

@ -113,8 +113,6 @@ class MyDataset(Dataset):
def load_data(self, idx): def load_data(self, idx):
text, wav_file = self.items[idx] text, wav_file = self.items[idx]
wav = np.asarray(self.load_wav(wav_file), dtype=np.float32) wav = np.asarray(self.load_wav(wav_file), dtype=np.float32)
mel = None
linear = None
if self.use_phonemes: if self.use_phonemes:
text = self.load_phoneme_sequence(wav_file, text) text = self.load_phoneme_sequence(wav_file, text)
@ -128,9 +126,7 @@ class MyDataset(Dataset):
sample = { sample = {
'text': text, 'text': text,
'wav': wav, 'wav': wav,
'item_idx': self.items[idx][1], 'item_idx': self.items[idx][1]
'mel': mel,
'linear': linear
} }
return sample return sample
@ -193,17 +189,9 @@ class MyDataset(Dataset):
] ]
text = [batch[idx]['text'] for idx in ids_sorted_decreasing] text = [batch[idx]['text'] for idx in ids_sorted_decreasing]
# if specs are not computed, compute them. mel = [self.ap.melspectrogram(w).astype('float32') for w in wav]
if batch[0]['mel'] is None and batch[0]['linear'] is None: linear = [self.ap.spectrogram(w).astype('float32') for w in wav]
mel = [
self.ap.melspectrogram(w).astype('float32') for w in wav
]
linear = [
self.ap.spectrogram(w).astype('float32') for w in wav
]
else:
mel = [d['mel'] for d in batch]
linear = [d['linear'] for d in batch]
mel_lengths = [m.shape[1] + 1 for m in mel] # +1 for zero-frame mel_lengths = [m.shape[1] + 1 for m in mel] # +1 for zero-frame
# compute 'stop token' targets # compute 'stop token' targets