ringger/transcribe-critic

Multi-source transcript merging inspired by textual criticism — LLM adjudicates multiple Whisper, YouTube captions & external transcripts for higher quality. Includes speaker diarization and summarization.

48
/ 100
Emerging

Aligns multiple transcript sources using wdiff-based longest common subsequence matching, then presents blind A/B/C comparisons to an LLM to resolve disagreements without source bias. Runs multiple Whisper models by default (small, medium, distil-large-v3) and integrates YouTube captions, external transcripts, speaker diarization via pyannote.audio, and slide extraction — all with checkpoint resumption and a make-style DAG pipeline that skips redundant work.

Available on PyPI.

Maintenance 13 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 6 / 25

How are scores calculated?

Stars

14

Forks

1

Language

Python

License

MIT

Last pushed

Mar 09, 2026

Monthly downloads

526

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ringger/transcribe-critic"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.