repoGitLabTrust 82 · PrimaryPublished 22d agoLive · 22d ago
mohaiminul-sust/yt-babel
Downloads a YouTube video, transcribes it with faster-whisper or DeepInfra Whisper, optionally translates the subtitles to English and/or Bengali via a local or cloud LLM, synthesizes TTS audio tracks, and soft-codes everything back into the video with ffmpeg.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%NagaTranslate: Building a translation and voice pipeline for low-resource Nagaland creoles (Whisper, VITS, LLMs) [P] →
- PossiblePossibly related (embedding) · 48%Fluid, natural voice translation with Gemini 3.5 Live Translate →
