VoiceStreamAI icon indicating copy to clipboard operation
VoiceStreamAI copied to clipboard

Published 20 hours ago • verified publisher icon alesaccoia

Prioritize GPU Over CPU for Initial Loading of OpenAI Whisper Model

Open jinmiaoluo opened this issue 8 months ago • 0 comments

Loading the OpenAI Whisper model into the GPU firstly instead of RAM using CPU.

Currently, our app only loads the OpenAI Whisper model into RAM using the CPU, instead of primarily using the GPU.

jinmiaoluo avatar Jun 01 '24 12:06 jinmiaoluo