lucidrains / naturalspeech2-pytorch

Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch
MIT License
1.26k stars 100 forks source link

multiple GPU? #39

Open a897456 opened 5 months ago

a897456 commented 5 months ago

image Hi, @lucidrains I found that when step=1000, the system could save the .pt file automatically and output two audio files at the same time, but at this time, a single GPU always reports an error above. I plan to use multiple GPU, but you don't seem to provide how to use multiple GPU. can you show it ?