VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
6.48k
stars
1.21k
forks
source link
Are there any bug in voice_conversion (reverse True or False for source and target) ?? #148
Open
yt605155624 opened 1 year ago
https://github.com/jaywalnut310/vits/blob/2e561ba58618d021b5b8323d3765880f7e0ecfdb/models.py#L525
in Glow-TTS Appendix B3, you said that
so I think
reverse
should beTrue
in https://github.com/jaywalnut310/vits/blob/2e561ba58618d021b5b8323d3765880f7e0ecfdb/models.py#L530 and should beFalse
(by default) in https://github.com/jaywalnut310/vits/blob/2e561ba58618d021b5b8323d3765880f7e0ecfdb/models.py#L531