YE Zhen
YE Zhen
i think so
You can refer to diffsinger's code to reproduce it. I will release this part of the code later.
Diffsinger with EDM diffusion configuration
Our method can also be applied to English singing voice, but you would need to collect the data yourself.
released
next month.
Thank you for your interest and your questions! 1, Yes, the baseline acoustic codec excludes the entire blue block in Figure 1. 2, We used their released checkpoints for both...
Sorry, I have now updated the links for the YAML file and I apologize for the inconvenience earlier.
Sorry, I have also updated.
What's your WeChat ID, or you can send me an email at [email protected].