☆ Yσɠƚԋσʂ ☆ to ProgrammingEnglish · 5 months agoMade a script that pulls MP3s from YouTube podcasts, transcribes them with WhisperX, and then uses an LLM to generate a summary. It works surprisingly well.git.sr.htexternal-linkmessage-square12linkfedilinkarrow-up125arrow-down12 cross-posted to: technology@hexbear.netprogramming@lemmy.ml
arrow-up123arrow-down1external-linkMade a script that pulls MP3s from YouTube podcasts, transcribes them with WhisperX, and then uses an LLM to generate a summary. It works surprisingly well.git.sr.ht☆ Yσɠƚԋσʂ ☆ to ProgrammingEnglish · 5 months agomessage-square12linkfedilink cross-posted to: technology@hexbear.netprogramming@lemmy.ml
minus-squareCommiejoneslinkfedilinkarrow-up1·5 months agoJust had a thought. Maybe you could just snatch the Youtube generated transcript instead.
minus-square☆ Yσɠƚԋσʂ ☆OPlinkfedilinkarrow-up2·5 months agoYeah, the script will try doing that by default now, and if it can’t then it falls back to transcribing the audio. Also switched to parakeet from whisperx cause it’s way faster.
Just had a thought. Maybe you could just snatch the Youtube generated transcript instead.
Yeah, the script will try doing that by default now, and if it can’t then it falls back to transcribing the audio. Also switched to parakeet from whisperx cause it’s way faster.