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

Model Conversion of Hindi lang (Fastpitch and Hifigan ) model to nemo and RIva #31

Open
rthoke opened this issue Oct 1, 2024 · 0 comments

Comments

@rthoke
Copy link

rthoke commented Oct 1, 2024

I have Hindi models for FastPitch (for text-to-speech) and HiFi-GAN (for vocoding). These models need to be integrated with NVIDIA NeMo for efficient deployment in Riva. The goal is to utilize the full capabilities of Riva’s real-time ASR/TTS pipeline with Hindi language support.

Tasks:
Model Conversion:

Convert the trained FastPitch and HiFi-GAN models into the NeMo format.
Ensure proper handling of Hindi language-specific phonetic and tonal characteristics during the conversion.
Export to Riva:

Convert the NeMo models to a format compatible with NVIDIA Riva for deployment.
Validate that both the FastPitch and HiFi-GAN models are functional after deployment in Riva’s speech synthesis pipeline.

[Any guidelines or existing examples on converting FastPitch/HiFi-GAN models to NeMo format.]
[Documentation or tutorials for integrating these models with Riva, especially for non-English languages like Hindi.]
[Suggestions for addressing potential language-specific challenges in the conversion process]

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

1 participant