Apply for community grant: Academic project (gpu)

#1
by RMSnow - opened
Amphion org

Hi! We've developed a versatile voice imitation system called Vevo (which is accpected by ICLR 2025), and we've open-sourced the code and checkpoints. It was trained on a multilingual dataset of over 100,000 hours, supporting Chinese, English, Japanese, French, German, and Korean. We've showcased audio samples at https://versavoice.github.io/, and our paper can be found at https://arxiv.org/abs/2502.07243.

Hi @RMSnow , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.

Sign up or log in to comment