Skip to content
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

DiffSinger: support different dictionaries for Chinese, Japanese and Cantonese #1006

Merged
merged 6 commits into from
Jan 28, 2024

Conversation

oxygen-dioxide
Copy link
Contributor

  • DiffSinger voicebanks can use different dictionaries for Chinese (dsdict-zh.yaml), Japanese (dsdict-ja.yaml) and Cantonese (dsdict-zh-yue.yaml). For example, DiffSinger Chinese phonemizer tries to load dsdict-zh.yaml first. If dsdict-zh.yaml isn't found, it will load dsdict.yaml as before. This will make it easier to develop multilingual voicebanks.
    • This change doesn't affect existing voicebanks.
  • Add DiffSinger Japanese phonemizer (DIFFS JA). Currently the only difference between DIFFS JA and DIFFS is that DIFFS JA tries to load dsdict-ja.yaml before loading dsdict.yaml.
  • Moved diffsinger phonemizer code to a subfolder.

@stakira
Copy link
Owner

stakira commented Jan 25, 2024

conflict

@stakira stakira merged commit 6f3b7b6 into stakira:master Jan 28, 2024
3 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants