CPU vs GPU - Inference Command Line

[markbland82]

I am running the inference cli command line but it is only using my CPU, is there a reason for this? I have a GPU (3080ti,12gb) which I assume would be able to process the inference much more quickly. Am I missing something? Thanks!

[SWivid]

check here https://github.com/SWivid/F5-TTS#:~:text=%23%20Create%20a,few%20options%20below%3A

[thesandi99]

run infer_gradio - make sure cuda is in place check cuda

import torch print("CUDA Available:", torch.cuda.is_available()) print("CUDA Version:", torch.version.cuda) print("Number of GPUs:", torch.cuda.device_count()) print("GPU Name:", torch.cuda.get_device_name(0) if torch.cuda.is_available() else "No GPU")
2. may u use ubuntu (recommeded) if not use it :] if u use window may internel issue i dont know
3. if u use ubuntu the

goto => task maneger => click processer in top => right click python (code)=> click alt + s then see magic

[markbland82]

Looks like there were some issues with my venv, likely Torchvision/Audio/Torch causing a break. Torchvision 0.18.0+cu118 appears to have fixed it from what I can tell.

Thanks for taking the time! F5 is outstanding! Looking forward to future updates @SWivid :) Cheers!