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
107,098 visible repositories in the index
1–24 of 69 · Most stars
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.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Toolkit for linearizing PDFs for LLM datasets/training
pix2tex: Using a ViT to convert images of equations into LaTeX code.
TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M
OCR & Document Extraction using vision models
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ https://greasyfork.org/en/scripts/437569-cotrans-manga-image-translator-regular-edition
The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
(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
All-in-One Development Tool based on PaddlePaddle
yolo3+ocr
Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.
A Unified Toolkit for Deep Learning Based Document Image Analysis
TranslatedYet another computer-aided comic/manga translation tool powered by deeplearning. Supports one-click machine translation and simple image/text editing.
Use OCR in Windows quickly and easily with Text Grab. With optional background process and notifications.
Scan documents to PDF and more, as simply as possible.
OpenMMLab Text Detection, Recognition and Understanding Toolbox
Free and open-source PDF editor for Windows with its own PDF 2.0 engine. View, annotate, OCR, edit text, redact, sign, fill forms, compare, merge, split and export to Word, Excel and PowerPoint. Reads EPUB and DjVu. No account, no subscription.
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】