Awesome
<div align="center"> <h1> X·SING: VISinger & Grad-SVC & NSF-BigVGAN </h1>Some thing as this paper : Make-A-Voice: Unified Voice Synthesis With Discrete Representation
</div>- Adapt VISinger for S1
- Adapt Grad-SVC for S2
- Adapt NSF-BigVGAN for S3