search

gemelo-ai / vocos

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
https://gemelo-ai.github.io/vocos/
MIT License
772 stars 88 forks source link

Multiple GPU #24

Open alexgain opened 1 year ago

alexgain commented 1 year ago

Hello, does the repository support multiple GPU inference with DataParallel? Or some other method?

Primarily, I'm looking for encoding with encodec and running that on multiple GPU (using codes and feature extractor, etc). Multi GPU with decoding via vocos would also be great.

Jackiexiao commented 1 year ago

see https://lightning.ai/docs/pytorch/stable/accelerators/gpu_basic.html

change here https://github.com/charactr-platform/vocos/blob/86db50a025ecaddf864366d5dbfc83554ceedc60/configs/vocos.yaml#L86C15-L86C15