RunPod•2mo ago

Is Runpod's Faster Whisper Set Up Correctly for CPU/GPU Use?

Hi, I'm currently using Faster Whisper provided by Runpod. https://github.com/runpod-workers/worker-faster_whisper While reviewing the code, I found something confusing: https://github.com/runpod-workers/worker-faster_whisper/blob/main/builder/fetch_models.py#L15 Is there a specific reason for using "cpu" instead of "gpu"? Thanks!

GitHub

🎧 | RunPod worker of the faster-whisper model for Serverless Endpoint. - runpod-workers/worker-faster_whisper

GitHub

🎧 | RunPod worker of the faster-whisper model for Serverless Endpoint. - runpod-workers/worker-faster_whisper

1 Reply

nerdylive•2mo ago

i guess this is the relevant answer, duplicate question from general: https://discord.com/channels/912829806415085598/948767517332107274/1302180007174737951 it is for downloading the model