glancer VS yt-whisper

I had a huge backlog of tech videos, so I wrote me this (also to play a bit with Haskell, the base idea can be replicated easily in any language though): https://github.com/rberenguel/glancer

At work, most of my projects related to high volume data processing, with a focus on keeping costs low and performance high. Out of work, I like working on many different things, like custom productivity tools (like this one to save time watching technical presentations) or creating generative artwork.

I did a similar (in spirit, to save time) thing [1] to be able to skim on technical presentations: it creates a static HTML page with regular shots from the video with the corresponding Youtube CC on the side. It can help decide if a presentation is worth a watch (or just get the gist of one). Uses youtube-dl and ffmpeg under the hood.

[1]: https://github.com/rberenguel/glancer

I have some live (as in in code I use) examples here: https://github.com/rberenguel/glancer/blob/main/src/Process.hs#L36 (using readProcess and callProcess)

#28 transcribe local files

Or even better, yt-whisper, which uses OpenAI's Whisper speech to text. I guess it'd be better to first check whether the video has captions first before Whispering, so maybe both your command and this one could be used together.

https://github.com/m1guelpf/yt-whisper

With minimal changes to https://github.com/m1guelpf/yt-whisper i got a setup to transcribe subs from YouTube videos or local files bit it might take an hour or so running the large model on my CPU.