Skip to content

1.0 Demo Combo Model

Latest
Compare
Choose a tag to compare
@CNChTu CNChTu released this 17 Jul 07:04
77d4188

Shallow diffusion model:
k_step_max=100
unit encoder: contentvec768l12
training 600000 steps without pretrain model
network: 512*20
speaker1: opencpop
speaker2: kiritan
Naive model:
unit encoder: contentvec768l12
training 200000 steps without pretrain model
speaker1: opencpop
speaker2: kiritan