a haswell xeon e5-1650 machine, i remember running llama 7b in llama.cpp in like 2023 and it was quite sluggish. guess i should try whisper at some point..
i don't use it at all, i do want some selfhosted speech to text model (whisper?) but my computer is ancient so it would be awfully slow. i have some multi hour audio recordings from presentations, would be nice to have them in text and searchable..
webrecorder browsertrix should work for this. they even have a hosted/paid service which could be better than selfhosting depending on the circumstance.
saving as html with singlefile and sharing manually could be easier/simpler, the concept is easy to understand for non computer people imo.
other than that i recently found out hoardy-web, doesn't really fit your usecase as this is basically saving everything you see on your browser for personal archiving though. very well made but somehow it isn't as widely known as other stuff in this area..
the idea sounds interesting and its also similar to what ive considered making some time ago. but why tf did you mess it up with this ai slop wall of text? heck, i'd even understand if you used LLMs in the code due to lack of skills, i'm also not a good programmer and i'm sympathetic. but there's really no reason for having this entire post written by an LLM.
can confirm cows/chickens/pigs apply as well..