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

Add missing languages to configuration definitions. #419

Merged
merged 1 commit into from
Oct 22, 2024

Conversation

koukisdevki
Copy link
Contributor

XTTS supports 17 languages, and whisper supports all of those languages. This adds extra languages to the configuration. See: discord dev post.

@KissAxel
Copy link

Hello! What makes a language supported? If the XTTS is xVASynth there are more languages right? Can you educate me on the subject a little? I'm trying to make norwegian work and test around, and publish my results!

@koukisdevki
Copy link
Contributor Author

Hello! What makes a language supported? If the XTTS is xVASynth there are more languages right? Can you educate me on the subject a little? I'm trying to make norwegian work and test around, and publish my results!

Its the 2 letter language that is used by mantella's python script for TTS and STT. What we have here is all those language supported by XTTS, but whisper should support a lot more (see https://platform.openai.com/docs/guides/speech-to-text/quickstart).

In the setup that I have, I use a different language for STT and english for TTS. So you can speak, in lets say Norwegian, and that text will get passed to the LLM, but you set the prompt so it always returns text in English, and so the TTS will read it in english. You can have a separate language for STT and another one for TTS.

@art-from-the-machine art-from-the-machine merged commit ac919d4 into art-from-the-machine:main Oct 22, 2024
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.

3 participants