I indexed 37h of my YouTube library using an RTX 4090 and local ML models in 24h

TLDR: I indexed 37 hours and 38 minutes of my videos using the self-hosted Docker version of my project on a rented RTX 4090

- Total compute time: 24 hours 13 minutes

- Frame analysis took ~85% of the time

- Heaviest plugins: TextDetection (especially on coding/screen recordings) and FaceRecognition (on podcasts)

Full article here: https://iliashaddad.com/blog/i-indexed-37h-of-my-youtube-library-using-an-rtx-4090-and-local-ml-models-in-24h

5 points | by iliashad 18 hours ago

3 comments

iliashad 18 hours ago
and the project is fully open source here: https://github.com/iliashad/edit-mind
toomuchtodo 18 hours ago
Does this support an S3 compatible target? If not, would you be interested in adding support for that?
[-]
- iliashad 17 hours ago
  Currently, not. Because the project is intended for local video files.
  I added it as a GitHub issue: https://github.com/IliasHad/edit-mind/issues/159.
  Btw, feel free to contribute to the project :)
videotextly 7 hours ago
[flagged]