Mirrors/TTS
1
0
Fork 0
mirror of https://github.com/coqui-ai/TTS.git synced 2025-12-25 12:49:29 +01:00
Code Issues Packages Projects Releases Wiki Activity

check for speaker id is None before put on cuda

Browse Source
This commit is contained in:
Thomas Werkmeister
2019-07-17 14:08:53 +02:00
committed by GitHub
parent 1468db0d07
commit ee4d55549d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
utils/synthesis.py
View File

@@ -108,7 +108,7 @@ def synthesis(model,
# preprocess the given text
inputs = text_to_seqvec(text, CONFIG, use_cuda)
speaker_id = id_to_torch(speaker_id)
if use_cuda:
if speaker_id is not None and use_cuda:
speaker_id = speaker_id.cuda()
# synthesize voice
decoder_output, postnet_output, alignments, stop_tokens = run_model(