JulianFP / project-W

A self-hostable platform on which users can create transcripts of their audio files (speech-to-text) using Whisper AI
GNU Affero General Public License v3.0
2 stars 0 forks source link

Add summarize feature with LLMs #32

Open JulianFP opened 5 months ago

JulianFP commented 5 months ago

Sometimes you may want to get a summary for a long interview/talk/meeting/... after transcribing them. LLMs a great for this kind of job however they often come with similar privacy issues as whisper (ChatGPT, Gemini, ... are not self-hostable!). If we would provide something like that using a self-hosted LLM like llama or mistral it would make this kind of thing a lot more convenient for the user and prevent them from just copy and pasting the transcript into ChatGPT (and thus eliminating every benefit of this project).