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

v0.26.0 #338

Merged
merged 32 commits into from
Mar 10, 2025
Merged

v0.26.0 #338

merged 32 commits into from
Mar 10, 2025

Conversation

eginhard
Copy link
Member

Merge dev into main for release

eginhard and others added 30 commits January 16, 2025 14:01
Not manually checked. Generated with:
uv run ruff check tests/ TTS/ notebooks/ recipes/ --fix
Manually checked and adjusted after generating with:
uv run ruff check tests/ TTS/ notebooks/ recipes/ --fix --unsafe-fixes
* docs: clean up server README

* docs: formatting

---------

Co-authored-by: Enno Hermann <enno.hermann@idiap.ch>
Switch remaining CLI tests to Python, separate integration tests
* Added speaker_wav parameter to the server

* Check if speaker_id is not empty

* feat(server): add input field for speaker_wav

---------

Co-authored-by: Enno Hermann <enno.hermann@idiap.ch>
XTTS accepts a `speed` parameter, but that was previously captured in the API
which prevented it from being passed through. Removing the non-functional
`speed` parameter from the API lets it pass via `kwargs` to models that support
it.
Refactor for compatibility with transformers>=4.47
This makes it possible to use --continue_path with XTTS
Added new persian-tts-female-vits model
@eginhard eginhard merged commit 746c377 into main Mar 10, 2025
33 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.

6 participants