代码库
Fast CPU OCR: line detection, CTC recognition, reading order, markdown
Python
aicpudocument-parsingocronnxpdf
A consistent, fair, benchmark for structured extraction.
Python
benchmarkextractionnlpocr
OCR model that handles complex tables, forms, handwriting with full layout.
Python
aiocr
OCR, layout analysis, reading order, table recognition in 90+ languages
Python
Convert PDF to markdown + JSON quickly with high accuracy
Python