Catch OOM and run whisper on cpu automatically. #117

zim33 · 2023-03-12T04:50:49Z

zim33 commented

2023-03-12 04:50:49 +00:00

For users wishing to run larger whisper model but lack VRAM, run it on CPU.

zim33 added 1 commit 2023-03-12 04:50:50 +00:00

Catch OOM and run whisper on cpu automatically. 61500107ab

mrq merged commit 8ed09f9b87 into master

2023-03-12 05:09:54 +00:00

mrq deleted branch vram

2023-03-12 05:09:54 +00:00

mrq referenced this issue from a commit

2023-03-12 05:09:57 +00:00

Merge pull request 'Catch OOM and run whisper on cpu automatically.' (#117) from zim33/ai-voice-cloning:vram into master

mrq commented

2023-03-12 05:09:57 +00:00

Ah, I don't know why I didn't think to check if there was a way to set it to CPU only for openai/whisper.

I suppose for Windows users with low GPU VRAM but high enough system VRAM, this will do fine, but I'd prefer Linux users to use WhisperCPP, as the models are just as good but use less RAM.

Ah, I don't know why I didn't think to check if there was a way to set it to CPU only for openai/whisper. I suppose for Windows users with low GPU VRAM but high enough system VRAM, this will do fine, but I'd prefer Linux users to use WhisperCPP, as the models are just as good but use less RAM.

Sign in to join this conversation.

No reviewers