New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
VISinger #4689
VISinger #4689
Conversation
Added midi, tempo, and beat embedding
note that dict is used instead of tuple, according to the latest vits model format, which may affect other svs models.
This pull request is now in conflict :( |
stage 8 (evaluation) causes an error because the names of ground truth wav files differ from generated files. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Many thanks for the update! The implementation is cool. I only have some minor comments. Please fix them, then we can get into the next stage. Good job!
After you fixes the two issues pointed out, I will merge this PR and we can work on the one that merges into the master branch. |
Implement VISinger model