πŸ† #414 overall#65 of 313 in OCR & Documents

breezedeus /Pix2Text

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

$ git clone https://github.com/breezedeus/Pix2Text.git
GitHub social preview for breezedeus/Pix2Text
Stars
3.3K
3,253
Forks
283
283
Language
Jupyter Notebook
License
MIT
Created
Sep 7, 2022
4.0 years old
Last push
Aug 23, 2026

Categories

GitHub topics

More in OCR & Documents

OCR & Documents

bytedance/Dolphin

The official repo for β€œDolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

PythonOtherupdated Mar 25, 2026
GitHub β†—β˜… 9.1Kβ‘‚ 778
OCR & Documents

RQLuo/MixTeX-Latex-OCR

MixTeX multimodal LaTeX, ZhEn, and, Table OCR. It performs efficient CPU-based inference in a local offline on Windows.

PythonAGPL-3.0updated Apr 24, 2025
GitHub β†—β˜… 1.6Kβ‘‚ 98
OCR & Documents

kotaro-kinoshita/yomitoku

YomiTokuはAIγ‚’ζ΄»η”¨γ—γŸζ—₯本θͺžζ–‡ζ›Έθ§£ζžγ‚¨γƒ³γ‚Έγƒ³γ‚’提供するPythonパッケージです。 Yomitoku is an AI-powered document image analysis package designed specifically for the Japanese language.

Pythonno licenseupdated Sep 14, 2026
GitHub β†—β˜… 1.6Kβ‘‚ 60
OCR & Documents

opendatalab/MinerUπŸ”₯ active

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

PythonOtherupdated Sep 24, 2026
GitHub β†—β˜… 80.6Kβ‘‚ 6.7K
OCR & Documents

ocrmypdf/OCRmyPDFπŸ”₯ active

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

PythonMPL-2.0updated Sep 22, 2026
GitHub β†—β˜… 34.9Kβ‘‚ 2.4K

Data from GitHub Β· snapshot Sep 24, 2026