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

convert from pytorch trained model to tensorflow #92

Open
nfaraji2002 opened this issue Jan 11, 2023 · 3 comments
Open

convert from pytorch trained model to tensorflow #92

nfaraji2002 opened this issue Jan 11, 2023 · 3 comments
Labels
enhancement New feature or request question Further information is requested

Comments

@nfaraji2002
Copy link

We have trained a pytorch Coqui TTS model for Persian language. How could we convert the model to a TFLite one to be executed on Raspberry 4?
Is there any other ways without conversion for running in real-time?
Thanks for your support.

@NeonBohdan
Copy link
Collaborator

neon-tts-plugin-coqui models has size of ~100MB and has RTF of 0.5 on Raspberry 4

@nfaraji2002
Copy link
Author

Thanks,
but I have a new trained model except 25 languages in this repository. Can we contribute to this TTS plugin for more languages?

@NeonBohdan
Copy link
Collaborator

Sure. You can provide dataset for us to train your language
Because your model may be slow and will not follow Raspberry Pi requirements

To check this can you send a link to the model or coqui config

@NeonDaniel NeonDaniel added enhancement New feature or request question Further information is requested labels May 16, 2024
@NeonDaniel NeonDaniel moved this to Low Priority in Community Projects May 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request question Further information is requested
Projects
Status: Low Priority
Development

No branches or pull requests

3 participants