search

McCloudS / subgen

Autogenerate subtitles using OpenAI Whisper Model via Jellyfin, Plex, Emby, Tautulli, or Bazarr
MIT License
641 stars 55 forks source link

Intel Arc GPU Support? #96

Closed jacobkossman closed 5 months ago

jacobkossman commented 5 months ago

Thanks for your work on this! I was wondering if you could add support for Intel GPUs as I have purchased an intel arc a380 for hardware transcoding and hoping to use it for this.

I found this docker image which includes the necessary things: https://github.com/mattcurf/whisper-intel-gpu to run whisper.

Additionally, is there a way to just run manually on a specific video file without a webhook? Ideally I'd be able to just run this on specific shows / episodes to generate subtitles for them. Thanks!

McCloudS commented 5 months ago

CTranslate/Faster-whisper doesn’t support Intel Arc.

You can use transcribe_folders set to an individual file or use the batch endpoint at /docs to do files without a webhook.