OnnxOCR
by jingsongliujing (personal account)
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed. (description from the project’s GitHub page)
Repository facts
- Stars
- 1,876
- Forks
- 200
- Open issues and pull requests
- 47
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- jingsongliujing · Personal account
- Created
- Jul 8, 2023
- Last push
- Jun 11, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,189: ankandrew/fast-plate-ocr
Lightweight & fast OCR models for license plate text recognition.
783 starsPythonMITLast push Mar 14, 2026
Rank 1,408: Layout-Parser/layout-parser
A Unified Toolkit for Deep Learning Based Document Image Analysis
5,775 starsPythonApache-2.0Last push Aug 15, 2024
Rank 2,409: deepdoctection/deepdoctection
A Repo For Document AI
3,265 starsPythonApache-2.0Last push Sep 14, 2026
Rank 6,857: ankandrew/fast-alpr
Fast Automatic License Plate Recognition (ALPR) framework.
837 starsPythonMITLast push Mar 16, 2026
Rank 759: CVHub520/X-AnyLabeling
X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, point cloud and multimodal data, combining versatile bui…
10,729 starsPythonGPL-3.0Last push Oct 18, 2026
Rank 1,807: openvinotoolkit/open_model_zoo
Pre-trained Deep Learning models and demos (high quality and extremely fast)
4,437 starsPythonApache-2.0Last push Oct 15, 2026