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

load audio change

This commit is contained in:
Eren G 2018-07-30 13:51:25 +02:00
parent 2d37abead7
commit c6229316c6
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
datasets/LJSpeech.py
View File

@ -30,7 +30,7 @@ class MyDataset(Dataset):
def load_wav(self, filename): def load_wav(self, filename):
try: try:
audio = librosa.core.load(filename, sr=self.sample_rate) audio = librosa.core.load(filename, sr=self.sample_rate)[0]
return audio return audio
except RuntimeError as e: except RuntimeError as e:
print(" !! Cannot read file : {}".format(filename)) print(" !! Cannot read file : {}".format(filename))
@ -65,7 +65,7 @@ class MyDataset(Dataset):
text = self.frames[idx][1] text = self.frames[idx][1]
text = np.asarray(text_to_sequence( text = np.asarray(text_to_sequence(
text, [self.cleaners]), dtype=np.int32) text, [self.cleaners]), dtype=np.int32)
wav = np.asarray(self.load_wav(wav_name)[0], dtype=np.float32) wav = np.asarray(self.load_wav(wav_name), dtype=np.float32)
sample = {'text': text, 'wav': wav, 'item_idx': self.frames[idx][0]} sample = {'text': text, 'wav': wav, 'item_idx': self.frames[idx][0]}
return sample return sample