Visualization of the generative process

open-mmlab / Amphion

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

https://openhlt.github.io/amphion/

MIT License

4.45k stars 379 forks source link

Visualization of the generative process #124

Closed l1amw closed 6 months ago

l1amw commented 7 months ago

Hello, great work! I was wondering how to implement the visualization of the generative process mentioned in your paper, thanks.

RMSnow commented 7 months ago

Hi @l1amw, thanks for your attention! The amphion visualization part is under developing. We expect to release it in next month!

lmxue commented 6 months ago

Hi @l1amw, please pay attention to #141 as we are releasing the visualization component. Currently, Amphion supports SingVisio, a visualization tool for the diffusion model used in singing voice conversion. The underlying SVC model is MultipleContentsSVC. The web-based user interface is scheduled to be integrated into Amphion within one week.

yuantuo666 commented 6 months ago

Hi @l1amw, the visualization component has been released now. You may check the details here. If you have any further questions about visualization, feel free to re-open this issue. We are glad to follow up!