Home

Awesome

DiffSinger (OpenVPI maintained version)

arXiv downloads Bilibili license

This is a refactored and enhanced version of DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism based on the original paper and implementation, which provides:

OverviewVariance ModelAcoustic Model
<img src="docs/resources/arch-overview.jpg" alt="arch-overview" style="zoom: 60%;" /><img src="docs/resources/arch-variance.jpg" alt="arch-variance" style="zoom: 50%;" /><img src="docs/resources/arch-acoustic.jpg" alt="arch-acoustic" style="zoom: 60%;" />

User Guidance

中文教程 / Chinese Tutorials: Text, Video

Progress & Roadmap

Architecture & Algorithms

TBD

Development Resources

TBD

References

Original Paper & Implementation

Generative Models & Algorithms

Dependencies & Submodules

Disclaimer

Any organization or individual is prohibited from using any functionalities included in this repository to generate someone's speech without his/her consent, including but not limited to government leaders, political figures, and celebrities. If you do not comply with this item, you could be in violation of copyright laws.

License

This forked DiffSinger repository is licensed under the Apache 2.0 License.