OCR model that handles complex tables, forms, handwriting with full layout.
Repository Index
68,760 visible repositories in the index
1–4 of 4 · Most stars
Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs
OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy