Retrieval-based-Voice-Conversion-WebUI icon indicating copy to clipboard operation
Retrieval-based-Voice-Conversion-WebUI copied to clipboard
verified publisher icon RVC-Project

[Feature Request] Nvidia Pytorch implementation of BigVGAN for higher quality and speed

Open tomakorea opened this issue 1 year ago • 0 comments

BigVGAN is a Universal Neural Vocoder with Large-Scale Training, it looks very robust even in extreme situations. Nvidia already made a Pytorch implementation of it here : https://github.com/NVIDIA/BigVGAN?tab=readme-ov-file

The audio demos seem to have quite a bump in quality over all other techniques : https://bigvgan-demo.github.io/

Would it be possible to implement it?

tomakorea avatar Jun 27 '24 14:06 tomakorea