How should we be using this model?

#1
by Hope2000 - opened

can you please provide any code to use the model?

This model was specifically made for the xVASynth editor, a Windows application. But the backend itself does not rely on anything Windows related.

I managed to create a HuggingFace space that only uses the backend:
https://huggingface.co/spaces/Pendrokar/xVASynth/tree/main

AFAIK the only other attempts on running it on a Linux system without the interface was just for the xVATrainer, which create xVAPitch models. For the purpose of using it on Google Colab:
https://colab.research.google.com/drive/15iLaCsZoW0mBT64fFo1xHszUHFYsgJOl?usp=sharing

I should probably remove the NeMo tag, as I don't think it was created to be compatible with the NeMo framework. This model just uses the NeMo provided audio datasets.

Thanks a lot for your response

I should probably remove the NeMo tag, as I don't think it was created to be compatible with the NeMo framework. This model just uses the NeMo provided audio datasets.

Done.

Pendrokar changed discussion status to closed

Sign up or log in to comment