Repository Index

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

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

• extract-data
• layout-analysis
• ocr
• parser

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.

• paddleocr
• ocr
• ocr-python
• umi-ocr

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

• python
• ocr
• pdf
• image-processing

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

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

Contexts Optical Compression

OCR, layout analysis, reading order, table recognition in 90+ languages

Toolkit for linearizing PDFs for LLM datasets/training

pix2tex: Using a ViT to convert images of equations into LaTeX code.

• machine-learning
• transformer
• im2latex
• deep-learning

TranslatedDaidai Didi (带带弟弟, "take little brother along") general-purpose captcha recognition OCR, PyPI version

• ocr
• ddddocr
• captcha

OCR model that handles complex tables, forms, handwriting with full layout.

• ai
• ocr

TranslatedAn entry-level project for face, video, and text detection and recognition.

• dlib
• opencv
• tesseract-ocr
• keras

TranslatedTranslate manga/image: one-click translation of text in all kinds of images https://cotrans.touhou.ai/ (no longer working)

• manga
• anime
• ocr
• deep-learning

Implementation of Nougat Neural Optical Understanding for Academic Documents

An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.

• agent
• llm-tools
• ocr
• vlm

Translated[Captcha Recognition - Training] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.

• captcha-recognition
• tensorflow-tutorials
• ocr
• tensorflow

1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy

• ai
• cpu
• document-parsing
• ocr

Xiaomi-OCR-0

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.

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.