search

agostini01 / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
0 stars 4 forks source link

Set application to run on a specific GPU device #2

Open agostini01 opened 4 years ago

agostini01 commented 4 years ago

This should work:

CUDA_VISIBLE_DEVICES=2,3 python demo_cli.py

But it currently does not, always assigning the work to device 0.

malithj commented 4 years ago 
import torch

torch.cuda.set_device(1)