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

TranslatedA concise and elegant Dictionary and Translator macOS App for looking up words and translating text. Works out of the box, supports offline OCR recognition, and supports Youdao Dictionary, 🍎 Apple System Dictionary, 🍎 Apple System Translation, OpenAI, Gemini, DeepL, Google, Bing, Tencent, Baidu, Alibaba, Niutrans (小牛), Caiyun, and Volcano Translate.

• dictionary
• translate
• app
• macos

The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.

• text-extraction
• document-intelligence
• metadata-extraction
• pdf-extraction

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

• document-analysis
• layout-analysis
• ocr
• parser

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

• ocr
• deep-learning
• document-recognition
• text-detection

(CGCSTCD'2017) An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations. CGCSTCD = China Graduate Contest on Smart-city Technology and Creative Design

• computer-vision
• machine-learning
• artificial-intelligence
• plate-recognition

High Performance Chinese License Plate Recognition Framework.

• deep-learning
• plate-recognition
• android
• cpp

Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.

• easyocr
• game-translation
• mlnet
• ocr

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.

Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding && Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities