OCR, layout analysis, reading order, table recognition in 90+ languages
Repository Index
47,133 repositories indexed
1–3 of 3 · Most stars
OCR model that handles complex tables, forms, handwriting with full layout.
WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.