search

CorentinJ / Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time
Other
51.65k stars 8.66k forks source link

Inference running on CPU instead of GPU #1161

Open AJMarsh1 opened 1 year ago

AJMarsh1 commented 1 year ago

Hello, I set up this project on my computer, and it works. However, it is rather slow and when starting through the cli it says that inference is using the CPU.

Is there something I can change to make inference GPU-dependent instead for the sake of performance?

pmcanneny commented 1 year ago

also wondering this. is there a simple setting somewhere?