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
6.48k stars 1.21k forks source link

torch2 compat #141

Open yoinked-h opened 1 year ago

yoinked-h commented 1 year ago

colab now uses torch2, so we have to put the return_complex flag; later we'll have to handle when return_complex = True , since it will be forced on

yoinked-h commented 1 year ago

(from what i know; this shouldnt give any issues on other versions)