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

Merge pull request #742 from fijipants/patch-3 

Fix GPU inference
This commit is contained in:
Eren Gölge 2021-08-26 22:11:03 +02:00 committed by GitHub
parent b02c4fe347 8f57f8adfd
commit 8f196fb01d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/utils/synthesizer.py
View File

@ -251,7 +251,7 @@ class Synthesizer(object):
d_vector=speaker_embedding, d_vector=speaker_embedding,
) )
waveform = outputs["wav"] waveform = outputs["wav"]
mel_postnet_spec = outputs["outputs"]["model_outputs"][0].detach().numpy() mel_postnet_spec = outputs["outputs"]["model_outputs"][0].detach().cpu().numpy()
if not use_gl: if not use_gl:
# denormalize tts output based on tts audio config # denormalize tts output based on tts audio config
mel_postnet_spec = self.ap.denormalize(mel_postnet_spec.T).T mel_postnet_spec = self.ap.denormalize(mel_postnet_spec.T).T