X·SING: VISinger & VITS-SVC & NSF-BigVGAN
Some thing as this paper : Make-A-Voice: Unified Voice Synthesis With Discrete Representation
- Adapt VISinger for S1
- Adapt VITS-SVC for S2
- Adapt NSF-BigVGAN for S3
Some thing as this paper : Make-A-Voice: Unified Voice Synthesis With Discrete Representation