coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use PWGAN if available in Synthesizer.tts

pull/10/head
Reuben Morais 2020-02-13 15:49:46 +01:00 committed by erogol
parent 60379271dc
commit 3b57e88a66
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
server/synthesizer.py
View File

@ -168,9 +168,16 @@ class Synthesizer(object):
postnet_output, decoder_output, _ = parse_outputs(
postnet_output, decoder_output, alignments)
if self.pwgan:
vocoder_input = torch.FloatTensor(postnet_output.T).unsqueeze(0)
if self.use_cuda:
vocoder_input.cuda()
wav = self.pwgan.inference(vocoder_input, hop_size=self.ap.hop_length)
if self.wavernn:
postnet_output = postnet_output[0].data.cpu().numpy()
wav = self.wavernn.generate(torch.FloatTensor(postnet_output.T).unsqueeze(0).cuda(), batched=self.config.is_wavernn_batched, target=11000, overlap=550)
vocoder_input = torch.FloatTensor(postnet_output.T).unsqueeze(0)
if self.use_cuda:
vocoder_input.cuda()
wav = self.wavernn.generate(vocoder_input, batched=self.config.is_wavernn_batched, target=11000, overlap=550)
else:
wav = inv_spectrogram(postnet_output, self.ap, self.tts_config)
# trim silence