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 support for MixerTTS and Vocos vocoder #1955

Open
mah92 opened this issue Mar 4, 2025 · 3 comments
Open

Add support for MixerTTS and Vocos vocoder #1955

mah92 opened this issue Mar 4, 2025 · 3 comments

Comments

@mah92
Copy link
Contributor

mah92 commented Mar 4, 2025

Hi
I am stunned by the voice quality and speed of this combination: MixerTTS and Vocos vocoders from here and here.

  • The voice quality is good.
  • The speed is excellent on smart phones(5x faster than the fastest possible matcha-tts and vits models I trained)
  • It supports arabic for now, but MixerTTS is an end to end model converting text to mels, so it is much easier to train (no need for messy vowelizers and dictionaries). It is much better for western Asian and African languages(Arabic, Farsi, Urdu, Kurdi, Pashtoo, ...).
    P.N: I compiled and put the test android app here
@csukuangfj
Copy link
Collaborator

@mah92 Would you mind contributing to add them?

@mah92
Copy link
Contributor Author

mah92 commented Mar 4, 2025

It needs much knowledge. I would need your extreme help... Specially for merging... I need you to continue my work if I failed...
Would you?

@csukuangfj
Copy link
Collaborator

If you have a working version, I can help review the code before merging it. Otherwise, I don't have time to support it.

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

No branches or pull requests

2 participants