ses4255/Versatile-OCR-Program

Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)

170 best points · 38 comments · 1 Hacker News post · 675 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: OCR pipeline for ML training (tables, diagrams, math, multilingual) (170 points, 38 comments, by ses425500000, 2025-04-05)