1.SoMarkAI / OXR
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
+1,532 stars
from 1,742 · score 7.33
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
26 repositories by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
2.baidu / Unlimited-OCR
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
+1,340 stars
from 29,138 · score 7.20
+839 stars
from 21 · score 6.73
+763 stars
from 29 · score 6.64
5.opendatalab / MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
+438 stars
from 82,626 · score 6.08
6.PaddlePaddle / PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
- pp-structure
- document-parsing
- +7 more
+416 stars
from 91,797 · score 6.03
7.datalab-to / indra
1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy
+373 stars
from 1,252 · score 5.92
8.hiroi-sora / Umi-OCR
TranslatedOCR software, free and offline. Open-source, free offline OCR software. Supports screenshots/batch importing of images, PDF document recognition, excluding watermarks/headers and footers, and scanning/generating QR codes. Has built-in multi-language libraries.
+170 stars
from 48,233 · score 5.14
9.tesseract-ocr / tesseract
Tesseract Open Source OCR Engine (main repository)
- tesseract
- tesseract-ocr
- ocr
- lstm
- machine-learning
- ocr-engine
- +1 more
+126 stars
from 77,198 · score 4.84
10.LaoFeng-mouse / flyingmouse-format
飞鼠格式 FlyingMouse Format - Windows 免费文件格式转换工具（离线可用，内置 FFmpeg/LibreOffice/Poppler/Tesseract）。图片/文档/表格/PPT/PDF/音视频/WPS 格式互转 + OCR + 批量转换；音频仅支持普通格式。作者：牢蜂（LaoFeng）｜仅供个人免费使用，禁止商业售卖/转卖/套壳
- desktop-app
- electron
- ffmpeg
- file-converter
- format-converter
- libreoffice
- +4 more
+105 stars
from 6,907 · score 4.66
11.HIllya51 / LunaTranslator
视觉小说翻译器 / Visual Novel Translator
- galgame
- visual-novel
- translator
- reverse-engineering
- ocr
+90 stars
from 13,922 · score 4.51
12.datalab-to / chandra
OCR model that handles complex tables, forms, handwriting with full layout.
+67 stars
from 12,610 · score 4.22
13.ocrmypdf / OCRmyPDF
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
- python
- ocr
- image-processing
- tesseract
+63 stars
from 35,166 · score 4.16
14.Tencent / WeVisDoc
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.
+42 stars
from 469 · score 3.76
+39 stars
from 24,079 · score 3.69
16.datalab-to / surya
OCR, layout analysis, reading order, table recognition in 90+ languages
+37 stars
from 21,541 · score 3.64
17.sml2h3 / ddddocr
TranslatedDaidai Didi (带带弟弟, "take little brother along") general-purpose captcha recognition OCR, PyPI version
+25 stars
from 14,875 · score 3.26
18.naptha / tesseract.js
Pure Javascript OCR for more than 100 Languages 📖🎉🖥
- tesseract
- webassembly
- ocr
- javascript
- deep-learning
+12 stars
from 38,798 · score 2.56
19.JaidedAI / EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
- ocr
- deep-learning
- crnn
- pytorch
- lstm
- machine-learning
- +9 more
+11 stars
from 30,110 · score 2.48
20.allenai / olmocr
Toolkit for linearizing PDFs for LLM datasets/training
+8 stars
from 19,805 · score 2.20
+6 stars
from 11,471 · score 1.95
22.DayBreak-u / chineseocr_lite
超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
+5 stars
from 12,351 · score 1.79
23.lukas-blecher / LaTeX-OCR
pix2tex: Using a ViT to convert images of equations into LaTeX code.
- machine-learning
- transformer
- im2latex
- deep-learning
- image2text
- latex
- +11 more
+4 stars
from 16,600 · score 1.61
24.getomni-ai / zerox
OCR & Document Extraction using vision models
+4 stars
from 12,249 · score 1.61
+1 stars
from 11,095 · score 0.69
26.ss062353-prog / on-device-vision-model
On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese, English, Japanese and Korean.
+1 stars
from 202 · score 0.69