search

jaywalnut310 / vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
https://jaywalnut310.github.io/vits-demo/index.html
MIT License
6.53k stars 1.22k forks source link

multi-speaker error #70

Open sixyang opened 1 year ago

sixyang commented 1 year ago

I try multi-speaker with the inference jupyter code( vctk version), but it doesn't work when I simply change the speaker id. sid = torch.LongTensor([4]).cuda() I change 4 to 5 even 100, it always has no change, somebody has this problem? thanks!

kdrkdrkdr commented 1 year ago

Me too..

ORI-Muchim commented 1 year ago

RUN train_ms.py

kdrkdrkdr commented 1 year ago

thx. It solved!