Fellow developers, what used to be the go-to FOSS library for audio-to-text before Whisper crammed itself into every nook and cranny?

(I am not looking to produce reliable, absolutely correct transcriptions. I'm only looking for "best effort" transcriptions.)

I've been trying to use Whisper (faster-whisper, to be precise) and the process keeps getting killed in spite of the fact that I don't literally run out of memory. Oh and chunking audio, afaik, should be done on periods of silence? Uhh..

0

If you have a fediverse account, you can quote this note from your own instance. Search https://chaos.social/users/catileptic/statuses/114160433391909254 on your instance and quote it. (Note that quoting is not supported in Mastodon.)