mirror of https://github.com/jlengrand/tldw.git synced 2026-03-10 08:51:17 +00:00

Files

Robert 9ba1943c50 Creating a backup of the original repo for archival purposes

Storing state of repo + all files prior to merge in case of some future issue/losing track of a file.

2024-05-13 23:10:26 -07:00

Too Long, Didnt Watch

YouTube contains an incredible amount of knowledge, much of which is locked inside multi-hour videos. Let's extract and summarize with AI!

diarize.py - download, transrcibe and diarize audio
- yt-dlp - download audio tracks of youtube videos
- ffmpeg - decompress audio
- faster_whisper - speech to text
- pyannote - diarization
chunker.py - break text into parts and prepare each part for LLM summarization
roller-*.py - rolling summarization
- can-ai-code - interview executors to run LLM inference
compare.py - prepare LLM outputs for webapp
compare-app.py - summary viewer webapp

This project is under active development and is not ready for production use.