whisper-at on cuda:1 - Githubissues

YuanGongND / ltu

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

390 stars 36 forks source link

Open alexanderwerning opened 10 months ago

alexanderwerning commented 10 months ago

Hello, I am trying to setup the LTU-AS system for local inference. I got an error because I only have one GPU, is there a reason why whisper-at is moved to cuda:1 and not cuda:0? https://github.com/YuanGongND/ltu/blob/8f615aa226f1367e200ef6ab90cebdd5549a791f/src/ltu_as/inference_gradio.py#L35 I changed it to cuda:0 and it seems to work fine

Thanks!

YuanGongND commented 10 months ago

hi there,

thanks so much for pointing this out.

My bad, will fix this soon.

-Yuan