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

Iliashad indexed 37 hours and 38 minutes of his own YouTube video library in 24 hours and 13 minutes of total compute time using the self-hosted Docker version of his project on a rented RTX 4090, he reported on Hacker News. Frame analysis consumed roughly 85% of the processing time, with the TextDetection plugin the heaviest load on coding and screen recordings and FaceRecognition the heaviest on podcasts.

| Consider applying for YC's Winter 2027 batch Applications are open till November 2. https://www.ycombinator.com/apply/ Guidelines newsguidelines.html \| FAQ newsfaq.html \| Lists lists \| API https://github.com/HackerNews/API \| Security security.html \| Legal https://www.ycombinator.com/legal/ \| Apply to YC https://www.ycombinator.com/apply/ \| Contact mailto:hn@ycombinator.com | | | Hacker News news new newest \| past front \| comments newcomments \| ask ask \| show show \| jobs jobs \| submit submit | login login?goto=item%3Fid%3D50329475 | | | | I indexed 37h of my YouTube library using an RTX 4090 and local ML models in 24h item?id=50329475 | | | | 2 points by iliashad user?id=iliashad 19 minutes ago item?id=50329475 \| hide hide?id=50329475&goto=item%3Fid%3D50329475 \| past https://hn.algolia.com/?query=I%20indexed%2037h%20of%20my%20YouTube%20library%20using%20an%20RTX%204090%20and%20local%20ML%20models%20in%2024h&type=story&dateRange=all&sort=byDate&storyText=false&prefix&page=0 \| favorite fave?id=50329475 \| 3 comments item?id=50329475 | | | | 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 |