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

Tacotron1 + wavernn configuration fix 

Tacotron1 + wavernn configuration: corrected the input format for wavernn vocoder, converted spectrograms to mels
This commit is contained in:
fatihkiralioglu 2020-04-25 15:18:46 +03:00 committed by GitHub
parent fab74dd5be
commit 70a8210283
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
server/synthesizer.py
View File

@ -184,7 +184,12 @@ class Synthesizer(object):
vocoder_input.cuda() vocoder_input.cuda()
wav = self.pwgan.inference(vocoder_input, hop_size=self.ap.hop_length) wav = self.pwgan.inference(vocoder_input, hop_size=self.ap.hop_length)
elif self.wavernn: elif self.wavernn:
vocoder_input = None
if self.tts_config.model == "Tacotron" :
vocoder_input = torch.FloatTensor(self.ap.out_linear_to_mel(linear_spec = postnet_output.T).T).T.unsqueeze(0)
else:
vocoder_input = torch.FloatTensor(postnet_output.T).unsqueeze(0) vocoder_input = torch.FloatTensor(postnet_output.T).unsqueeze(0)
if self.use_cuda: if self.use_cuda:
vocoder_input.cuda() vocoder_input.cuda()
wav = self.wavernn.generate(vocoder_input, batched=self.config.is_wavernn_batched, target=11000, overlap=550) wav = self.wavernn.generate(vocoder_input, batched=self.config.is_wavernn_batched, target=11000, overlap=550)