PaddleOCR
将任何 PDF 或图像文档转化为结构化数据，供您的 AI 使用。这款强大而轻量级的 OCR 工具包，架起了图像/PDF 与大型语言模型之间的桥梁。支持 100 多种语言。『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.』
Main metrics
Overview
| Name With Owner | PaddlePaddle/PaddleOCR |
|---|---|
| Primary Language | Python |
| Program language | Python (Language Count: 13) |
| Platform | |
| License: | Apache License 2.0 |
| Release Count | 26 |
| Last Release Name | v3.3.1 (Posted on ) |
| First Release Name | v1.1.0 (Posted on ) |
| Created At | 2020-05-08 18:38:16 |
| Pushed At | 2025-11-03 21:50:18 |
| Last Commit At | |
| Stargazers Count | 62457 |
| Watchers Count | 495 |
| Fork Count | 9220 |
| Commits Count | 6753 |
| Has Issues Enabled | |
| Issues Count | 10172 |
| Issue Open Count | 199 |
| Pull Requests Count | 3012 |
| Pull Requests Open Count | 35 |
| Pull Requests Close Count | 698 |
| Has Wiki Enabled | |
| Is Archived | |
| Is Fork | |
| Is Locked | |
| Is Mirror | |
| Is Private |
