An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
Apache License 2.0
2.69k
stars
283
forks
source link
Change variance retaking masks from zero inputs to zero embeddings #104
There are 4 modifications to the variance retaking mechanism in this pull request:
NOTE: These modifications are backward-incompatible. All models involving pitch and variance predictions need to be re-trained.