diff --git a/README.md b/README.md index 6458242..62e081f 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,8 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/PaddlePaddle/PaddleOCR) · [上游 README](https://github.com/PaddlePaddle/PaddleOCR/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。

@@ -6,7 +11,7 @@ -

Global Leading OCR Toolkit & Document AI Engine

+

全球领先的 OCR 工具包与文档 AI 引擎

English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README_tcn.md) | [日本語](./readme/README_ja.md) | [한국어](./readme/README_ko.md) | [Français](./readme/README_fr.md) | [Русский](./readme/README_ru.md) | [Español](./readme/README_es.md) | [العربية](./readme/README_ar.md) @@ -29,24 +34,24 @@ English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README -**PaddleOCR converts PDF documents and images into structured, LLM-ready data (JSON/Markdown) with industry-leading accuracy. With 70k+ Stars and trusted by top-tier projects like Dify, RAGFlow, and Cherry Studio, PaddleOCR is the bedrock for building intelligent RAG and Agentic applications.** +**PaddleOCR 将 PDF 文档与图片转换为结构化、可直接用于 LLM 的数据（JSON/Markdown），具备业界领先的准确率。凭借 70k+ Stars，并受到 Dify、RAGFlow、Cherry Studio 等顶尖项目的信赖，PaddleOCR 是构建智能 RAG 与 Agentic 应用的基石。** -## 🚀 Key Features +## 🚀 核心特性 -### 📄 Intelligent Document Parsing (LLM-Ready) -> *Transforming messy visuals into structured data for the LLM era.* +### 📄 智能文档解析（LLM-Ready） +> *将杂乱的视觉内容转化为 LLM 时代的结构化数据。* -* **SOTA Document VLM**: Featuring **PaddleOCR-VL-1.6 (0.9B)**, the industry's leading lightweight vision-language model for document parsing. It achieves 96.3% accuracy on OmniDocBench v1.6, leads in text, formula, and table recognition, and shows significantly enhanced capabilities in ancient documents, rare characters, seals, and charts, with structured outputs in **Markdown** and **JSON** formats. -* **Structure-Aware Conversion**: Powered by **PP-StructureV3**, seamlessly convert complex PDFs and images into **Markdown** or **JSON**. Unlike the PaddleOCR-VL series models, it provides more fine-grained coordinate information, including table cell coordinates, text coordinates, and more. -* **Production-Ready Efficiency**: Achieve commercial-grade accuracy with an ultra-small footprint. Outperforms numerous closed-source solutions in public benchmarks while remaining resource-efficient for edge/cloud deployment. +* **SOTA 文档 VLM**：搭载 **PaddleOCR-VL-1.6 (0.9B)**，业界领先的轻量级文档解析视觉语言模型（Vision-Language Model）。在 OmniDocBench v1.6 上达到 96.3% 准确率，在文本、公式与表格识别方面领先，并在古籍、生僻字、印章与图表等场景具备显著增强能力，可输出 **Markdown** 与 **JSON** 结构化结果。 +* **结构感知转换**：由 **PP-StructureV3** 驱动，可将复杂 PDF 与图片无缝转换为 **Markdown** 或 **JSON**。与 PaddleOCR-VL 系列模型不同，它提供更细粒度的坐标信息，包括表格单元格坐标、文本坐标等。 +* **生产级效率**：以极小体积实现商业级准确率。在公开基准测试中优于众多闭源方案，同时保持边缘/云端部署所需的资源效率。 -### 🔍 Universal Text Recognition (Scene OCR) -> *The global gold standard for high-speed, multilingual text spotting.* +### 🔍 通用文字识别（场景 OCR） +> *高速多语言文字检测的全球黄金标准。* -* **100+ Languages Supported**: Native recognition for a vast global library. **PP-OCRv6** supports 50 languages with a single unified model (Chinese, English, Japanese, and 46 Latin-script languages) — no model switching needed for multilingual documents. -* **Complex Element Mastery**: Beyond standard text recognition, we support **natural scene text spotting** across a wide range of environments, including IDs, street views, books, and industrial components -* **Performance Leap**: PP-OCRv6 achieves **+4.6% detection** and **+5.1% recognition** accuracy over PP-OCRv5, surpassing mainstream Vision-Language Models. 5.2× CPU inference speedup end-to-end. +* **支持 100+ 种语言**：原生支持庞大的全球语言库。**PP-OCRv6** 以单一统一模型支持 50 种语言（中文、英文、日文及 46 种拉丁文字语言）——多语言文档无需切换模型。 +* **复杂要素驾驭**：除标准文字识别外，我们还支持多种环境下的**自然场景文字检测（natural scene text spotting）**，涵盖证件、街景、书籍与工业零部件等。 +* **性能跃升**：PP-OCRv6 相较 PP-OCRv5，检测准确率提升 **+4.6%**、识别准确率提升 **+5.1%**，超越主流视觉语言模型（Vision-Language Models）。端到端 CPU 推理加速 **5.2×**。

@@ -54,151 +59,147 @@ English | [简体中文](./readme/README_cn.md) | [繁體中文](./readme/README

-### 🛠️ Developer-Centric Ecosystem -* **Seamless Integration**: The premier choice for the AI Agent ecosystem—deeply integrated with **Dify, RAGFlow, Pathway, and Cherry Studio**. -* **LLM Data Flywheel**: A complete pipeline to build high-quality datasets, providing a sustainable "Data Engine" for fine-tuning Large Language Models. -* **One-Click Deployment**: Supports various hardware backends (NVIDIA GPU, Intel CPU, Kunlunxin XPU, and diverse AI Accelerators). +### 🛠️ 面向开发者的生态 +* **无缝集成**：AI Agent 生态的首选方案——与 **Dify、RAGFlow、Pathway、Cherry Studio** 深度集成。 +* **LLM 数据飞轮**：完整流水线用于构建高质量数据集，为大型语言模型微调提供可持续的「数据引擎」。 +* **一键部署**：支持多种硬件后端（NVIDIA GPU、Intel CPU、昆仑芯 XPU 及各类 AI 加速器）。 -## 📣 Recent updates +## 📣 近期更新 -### 🔥 2026.06.11: Release of PaddleOCR 3.7.0 -- PP-OCRv6 highlights: +### 🔥 2026.06.11：PaddleOCR 3.7.0 发布 +- PP-OCRv6 亮点： - - **Accuracy boost**: Medium tier achieves +4.6% detection and +5.1% recognition over PP-OCRv5_server, surpassing mainstream VLMs (Qwen3-VL-235B, GPT-5.5) with only 34.5M parameters. - - **50 languages unified**: Single model covers Chinese, English, Japanese, and 46 Latin-script languages — no model switching needed. - - **Specialized scenarios**: Major improvements in digital displays, dot-matrix characters, tire prints, and industrial text recognition. - - **Faster inference**: 5.2× CPU speedup (OpenVINO), 6.1× on Apple M4 (tiny), 0.13s on A100 GPU. - - **Three tiers for all scenarios**: tiny (1.5M) / small (7.7M) / medium (34.5M) for edge, mobile, and server deployment. - - **Model availability**: All models are available on [HuggingFace](https://huggingface.co/collections/PaddlePaddle/pp-ocrv6) and [ModelScope](https://www.modelscope.cn/collections/PaddlePaddle/PP-OCRv6). + - **准确率提升**：medium 档位相较 PP-OCRv5_server，检测提升 +4.6%、识别提升 +5.1%，仅以 34.5M 参数超越主流 VLM（Qwen3-VL-235B、GPT-5.5）。 + - **50 种语言统一模型**：单一模型覆盖中文、英文、日文及 46 种拉丁文字语言——无需切换模型。 + - **专项场景**：在数字显示屏、点阵字符、轮胎印痕与工业文字识别方面有重大改进。 + - **更快推理**：CPU 加速 5.2×（OpenVINO），Apple M4（tiny）上 6.1×，A100 GPU 上 0.13s。 + - **三档覆盖全场景**：tiny（1.5M）/ small（7.7M）/ medium（34.5M），分别适用于边缘、移动端与服务端部署。 + - **模型可用性**：所有模型均可从 [HuggingFace](https://huggingface.co/collections/PaddlePaddle/pp-ocrv6) 和 [ModelScope](https://www.modelscope.cn/collections/PaddlePaddle/PP-OCRv6). 获取
-2026.05.28: Release of PaddleOCR 3.6.0 +2026.05.28：PaddleOCR 3.6.0 发布 -- PaddleOCR-VL-1.6 highlights: +- PaddleOCR-VL-1.6 亮点： - - **New SOTA Accuracy**: Achieves over 96.3% on OmniDocBench v1.6, also sets new SOTA on OmniDocBench v1.5 and Real5-OmniDocBench, leading both open-source and proprietary solutions in text, formula, and table recognition. - - **Comprehensive Capability Upgrade**: Significant improvements in table, ancient document, and rare character recognition, with notably enhanced seal recognition, spotting, and chart understanding across multiple scenarios. - - **Seamless Migration**: Model architecture is fully consistent with PaddleOCR-VL-1.5, enabling zero-cost adaptation—swap and go. - - **Try it now**: Available on [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) or our [Official Website](https://www.paddleocr.com). + - **全新 SOTA 准确率**：在 OmniDocBench v1.6 上超过 96.3%，并在 OmniDocBench v1.5 与 Real5-OmniDocBench 上创下新的 SOTA，在文本、公式与表格识别方面同时领先开源与闭源方案。 + - **能力全面升级**：在表格、古籍与生僻字识别方面有显著提升，印章识别、检测与图表理解在多种场景下均有明显增强。 + - **无缝迁移**：模型架构与 PaddleOCR-VL-1.5 完全一致，可实现零成本适配——即换即用。 + - **立即体验**：可在 [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.6) 或我们的 [官方网站](https://www.paddleocr.com). 获取 +
-2026.04.21: Release of PaddleOCR 3.5.0 +2026.04.21：PaddleOCR 3.5.0 发布 -* **Flexible inference backends**: Seamlessly switch between Paddle static graph, Paddle dynamic graph, or Transformers. PaddleOCR is now deeply integrated with the Hugging Face ecosystem, and 20 major models support Transformers as the inference backend. -* **Office documents to Markdown**: Convert common document formats such as Word, Excel, and PowerPoint into Markdown. -* **DOCX export for parsed results**: The `PaddleOCR-VL` series, `PP-StructureV3`, and `PP-DocTranslation` now support exporting parsed results to DOCX for convenient viewing and editing in Microsoft Word. -* **Official browser inference SDK**: Released `PaddleOCR.js`, the official browser inference SDK that supports running `PP-OCRv5` directly in the browser. +* **灵活的推理后端**：可在 Paddle 静态图、Paddle 动态图或 Transformers 之间无缝切换。PaddleOCR 现已与 Hugging Face 生态深度集成，20 个主要模型支持以 Transformers 作为推理后端。 +* **Office 文档转 Markdown**：将 Word、Excel、PowerPoint 等常见文档格式转换为 Markdown。 +* **解析结果 DOCX 导出**：`PaddleOCR-VL` 系列、`PP-StructureV3` 和 `PP-DocTranslation` 现已支持将解析结果导出为 DOCX，便于在 Microsoft Word 中查看和编辑。 +* **官方浏览器推理 SDK**：发布 `PaddleOCR.js`，即官方浏览器推理 SDK，支持在浏览器中直接运行 `PP-OCRv5`。
-2026.01.29: Release of PaddleOCR 3.4.0 +2026.01.29：PaddleOCR 3.4.0 发布 -* PaddleOCR-VL-1.5 (SOTA 0.9B VLM): Our latest flagship model for document parsing is now live! - * **94.5% Accuracy on OmniDocBench**: Surpassing top-tier general large models and specialized document parsers. - * **Real-World Robustness**: First to introduce the **PP-DocLayoutV3** algorithm for irregular shape positioning, mastering 5 tough scenarios: *Skew, Warping, Scanning, Illumination, and Screen Photography*. - * **Capability Expansion**: Now supports **Seal Recognition**, **Text Spotting**, and expands to **111 languages** (including China’s Tibetan script and Bengali). - * **Long Document Mastery**: Supports automatic cross-page table merging and hierarchical heading identification. - * **Try it now**: Available on [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5) or our [Official Website](https://www.paddleocr.com). +* PaddleOCR-VL-1.5（SOTA 0.9B VLM）：我们最新的文档解析旗舰模型现已上线！ + * **OmniDocBench 上 94.5% 准确率**：超越顶级通用大模型和专业文档解析器。 + * **真实场景鲁棒性**：率先引入 **PP-DocLayoutV3** 算法用于不规则形状定位，攻克 5 大棘手场景：*倾斜、扭曲、扫描、光照与屏幕拍摄*。 + * **能力扩展**：现已支持 **印章识别（Seal Recognition）**、**文本检测（Text Spotting）**，并扩展至 **111 种语言**（包括中国藏文和孟加拉文）。 + * **长文档处理**：支持自动跨页表格合并与层级标题识别。 + * **立即体验**：可在 [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL-1.5) or our [Official Website](https://www.paddleocr.com).
-2025.10.16: Release of PaddleOCR 3.3.0 +2025.10.16：PaddleOCR 3.3.0 发布 -- Released PaddleOCR-VL: - - **Model Introduction**: - - **PaddleOCR-VL** is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. **This innovative model efficiently supports 109 languages and excels in recognizing complex elements (e.g., text, tables, formulas, and charts), while maintaining minimal resource consumption**. Through comprehensive evaluations on widely used public benchmarks and in-house benchmarks, PaddleOCR-VL achieves SOTA performance in both page-level document parsing and element-level recognition. It significantly outperforms existing solutions, exhibits strong competitiveness against top-tier VLMs, and delivers fast inference speeds. These strengths make it highly suitable for practical deployment in real-world scenarios. The model has been released on [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL). Everyone is welcome to download and use it! More introduction information can be found in [PaddleOCR-VL](https://www.paddleocr.ai/latest/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL.html). +- 发布 PaddleOCR-VL： + - **模型介绍**： + - **PaddleOCR-VL** 是一款面向文档解析的 SOTA、资源高效模型。其核心组件为 PaddleOCR-VL-0.9B，这是一款紧凑而强大的视觉语言模型（VLM），将 NaViT 风格的动态分辨率视觉编码器与 ERNIE-4.5-0.3B 语言模型相结合，以实现精准的元素识别。**该创新模型高效支持 109 种语言，擅长识别复杂元素（如文本、表格、公式和图表），同时保持极低的资源消耗**。通过在广泛使用的公开基准和内部基准上的全面评测，PaddleOCR-VL 在页面级文档解析和元素级识别方面均达到 SOTA 性能。它显著优于现有方案，与顶级 VLM 具备强劲竞争力，并提供快速推理速度。这些优势使其非常适合在实际场景中部署。模型已在 [HuggingFace](https://huggingface.co/PaddlePaddle/PaddleOCR-VL). 发布，欢迎所有人下载使用！更多介绍信息请参阅 [PaddleOCR-VL](https://www.paddleocr.ai/latest/version3.x/algorithm/PaddleOCR-VL/PaddleOCR-VL.html). - - **Core Features**: - - **Compact yet Powerful VLM Architecture**: We present a novel vision-language model that is specifically designed for resource-efficient inference, achieving outstanding performance in element recognition. By integrating a NaViT-style dynamic high-resolution visual encoder with the lightweight ERNIE-4.5-0.3B language model, we significantly enhance the model’s recognition capabilities and decoding efficiency. This integration maintains high accuracy while reducing computational demands, making it well-suited for efficient and practical document processing applications. - - **SOTA Performance on Document Parsing**: PaddleOCR-VL achieves state-of-the-art performance in both page-level document parsing and element-level recognition. It significantly outperforms existing pipeline-based solutions and exhibiting strong competitiveness against leading vision-language models (VLMs) in document parsing. Moreover, it excels in recognizing complex document elements, such as text, tables, formulas, and charts, making it suitable for a wide range of challenging content types, including handwritten text and historical documents. This makes it highly versatile and suitable for a wide range of document types and scenarios. - - **Multilingual Support**: PaddleOCR-VL Supports 109 languages, covering major global languages, including but not limited to Chinese, English, Japanese, Latin, and Korean, as well as languages with different scripts and structures, such as Russian (Cyrillic script), Arabic, Hindi (Devanagari script), and Thai. This broad language coverage substantially enhances the applicability of our system to multilingual and globalized document processing scenarios. + - **核心特性**： + - **紧凑而强大的 VLM 架构**：我们提出了一种专为资源高效推理设计的全新视觉语言模型，在元素识别方面表现卓越。通过将 NaViT 风格的动态高分辨率视觉编码器与轻量级 ERNIE-4.5-0.3B 语言模型集成，我们显著提升了模型的识别能力与解码效率。该集成在保持高精度的同时降低了计算需求，非常适合高效、实用的文档处理应用。 + - **文档解析 SOTA 性能**：PaddleOCR-VL 在页面级文档解析和元素级识别方面均达到最先进性能。它显著优于现有基于流水线的方案，并在文档解析方面与领先的视觉语言模型（VLM）具备强劲竞争力。此外，它擅长识别复杂文档元素，如文本、表格、公式和图表，适用于多种具有挑战性的内容类型，包括手写文本和历史文献。这使其高度通用，适用于广泛的文档类型和场景。 + - **多语言支持**：PaddleOCR-VL 支持 109 种语言，覆盖全球主要语言，包括但不限于中文、英文、日文、拉丁文和韩文，以及书写体系和结构各异的语言，如俄文（西里尔字母）、阿拉伯文、印地文（天城文）和泰文。这种广泛的语言覆盖大幅提升了我们系统在多语言和全球化文档处理场景中的适用性。 -- Released PP-OCRv5 Multilingual Recognition Model: - - Improved the accuracy and coverage of Latin script recognition; added support for Cyrillic, Arabic, Devanagari, Telugu, Tamil, and other language systems, covering recognition of 109 languages. The model has only 2M parameters, and the accuracy of some models has increased by over 40% compared to the previous generation. +- 发布 PP-OCRv5 多语言识别模型： + - 提升了拉丁字母识别的准确率与覆盖范围；新增对西里尔字母、阿拉伯文、天城文、泰卢固文、泰米尔文等文字体系的支持，覆盖 109 种语言的识别。模型仅含 2M 参数，部分模型的准确率较上一代提升超过 40%。
-2025.08.21: Release of PaddleOCR 3.2.0 +2025.08.21：PaddleOCR 3.2.0 发布 -- **Significant Model Additions:** - - Introduced training, inference, and deployment for PP-OCRv5 recognition models in English, Thai, and Greek. **The PP-OCRv5 English model delivers an 11% improvement in English scenarios compared to the main PP-OCRv5 model, with the Thai and Greek recognition models achieving accuracies of 82.68% and 89.28%, respectively.** +- **重要模型新增：** + - 新增英文、泰文和希腊文 PP-OCRv5 识别模型的训练、推理与部署。**PP-OCRv5 英文模型在英文场景下较主 PP-OCRv5 模型提升 11%，泰文和希腊文识别模型准确率分别达到 82.68% 和 89.28%。** -- **Deployment Capability Upgrades:** - - **Full support for PaddlePaddle framework versions 3.1.0 and 3.1.1.** - - **Comprehensive upgrade of the PP-OCRv5 C++ local deployment solution, now supporting both Linux and Windows, with feature parity and identical accuracy to the Python implementation.** - - **High-performance inference now supports CUDA 12, and inference can be performed using either the Paddle Inference or ONNX Runtime backends.** - - **The high-stability service-oriented deployment solution is now fully open-sourced, allowing users to customize Docker images and SDKs as required.** - - The high-stability service-oriented deployment solution also supports invocation via manually constructed HTTP requests, enabling client-side code development in any programming language. +- **部署能力升级：** + - **全面支持 PaddlePaddle 框架 3.1.0 和 3.1.1 版本。** + - **全面升级 PP-OCRv5 C++ 本地部署方案，现支持 Linux 和 Windows，功能与 Python 实现完全一致，准确率相同。** + - **高性能推理现支持 CUDA 12，可使用 Paddle Inference 或 ONNX Runtime 后端进行推理。** + - **高稳定性面向服务的部署方案现已完全开源，用户可根据需要自定义 Docker 镜像和 SDK。** + - 高稳定性面向服务的部署方案还支持通过手动构造 HTTP 请求调用，可使用任意编程语言进行客户端代码开发。 -- **Benchmark Support:** - - **All production lines now support fine-grained benchmarking, enabling measurement of end-to-end inference time as well as per-layer and per-module latency data to assist with performance analysis. [Here's](docs/version3.x/pipeline_usage/instructions/benchmark.en.md) how to set up and use the benchmark feature.** - - **Documentation has been updated to include key metrics for commonly used configurations on mainstream hardware, such as inference latency and memory usage, providing deployment references for users.** +- **基准测试支持：** + - **所有产线现均支持细粒度基准测试，可测量端到端推理时间以及逐层、逐模块延迟数据，辅助性能分析。[此处](docs/version3.x/pipeline_usage/instructions/benchmark.en.md)介绍如何配置和使用基准测试功能。** + - **文档已更新，包含主流硬件上常用配置的关键指标，如推理延迟和内存占用，为用户提供部署参考。** -- **Bug Fixes:** - - Resolved the issue of failed log saving during model training. - - Upgraded the data augmentation component for formula models for compatibility with newer versions of the albumentations dependency, and fixed deadlock warnings when using the tokenizers package in multi-process scenarios. - - Fixed inconsistencies in switch behaviors (e.g., `use_chart_parsing`) in the PP-StructureV3 configuration files compared to other pipelines. +- **Bug 修复：** + - 修复了模型训练时日志保存失败的问题。 + - 升级公式模型的数据增强组件以兼容较新版本的 albumentations 依赖，并修复多进程场景下使用 tokenizers 包时的死锁警告。 + - 修复了 PP-StructureV3 配置文件中开关行为（如 `use_chart_parsing`）与其他流水线不一致的问题。 -- **Other Enhancements:** - - **Separated core and optional dependencies. Only minimal core dependencies are required for basic text recognition; additional dependencies for document parsing and information extraction can be installed as needed.** - - **Enabled support for NVIDIA RTX 50 series graphics cards on Windows; users can refer to the [installation guide](docs/version3.x/installation.en.md) for the corresponding PaddlePaddle framework versions.** - - **PP-OCR series models now support returning single-character coordinates.** - - Added AIStudio, ModelScope, and other model download sources, allowing users to specify the source for model downloads. - - Added support for chart-to-table conversion via the PP-Chart2Table module. - - Optimized documentation descriptions to improve usability. +- **其他增强：** + - **分离核心依赖与可选依赖。基础文本识别仅需最少核心依赖；文档解析和信息提取的额外依赖可按需安装。** + - **在 Windows 上启用对 NVIDIA RTX 50 系列显卡的支持；用户可参考[安装指南](docs/version3.x/installation.en.md)了解对应的 PaddlePaddle 框架版本。** + - **PP-OCR 系列模型现支持返回单字符坐标。** + - 新增 AIStudio、ModelScope 等模型下载源，用户可指定模型下载来源。 + - 新增通过 PP-Chart2Table 模块支持图表转表格。 + - 优化文档描述以提升易用性。
+[History Log](https://paddlepaddle.github.io/PaddleOCR/latest/en/update/update.html)) -[History Log](https://paddlepaddle.github.io/PaddleOCR/latest/en/update/update.html) +## 🚀 快速开始 +### 第一步：在线体验 +PaddleOCR 官网提供了交互式**体验中心**和 **API**——无需配置，一键即可体验。 -## 🚀 Quick Start +👉 [访问官网](https://www.paddleocr.com)) -### Step 1: Try Online -PaddleOCR official website provides interactive **Experience Center** and **APIs**—no setup required, just one click to experience. +### 第二步：本地部署 +如需本地使用，请根据需求参考以下文档： -👉 [Visit Official Website](https://www.paddleocr.com) +- **PP-OCR 系列**：参见 [PP-OCR 文档](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/OCR.html)) +- **PaddleOCR-VL 系列**：参见 [PaddleOCR-VL 文档](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PaddleOCR-VL.html)) +- **PP-StructureV3**：参见 [PP-StructureV3 文档](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PP-StructureV3.html)) +- **更多功能**：参见 [更多功能文档](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/pipeline_overview.html)) -### Step 2: Local Deployment -For local usage, please refer to the following documentation based on your needs: +## 🧩 更多特性 -- **PP-OCR Series**: See [PP-OCR Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/OCR.html) -- **PaddleOCR-VL Series**: See [PaddleOCR-VL Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PaddleOCR-VL.html) -- **PP-StructureV3**: See [PP-StructureV3 Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/PP-StructureV3.html) -- **More Capabilities**: See [More Capabilities Documentation](https://www.paddleocr.ai/latest/en/version3.x/pipeline_usage/pipeline_overview.html) +- 将模型转换为 ONNX 格式：[获取 ONNX 模型](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/inference_deployment/others/obtaining_onnx_models.html).) +- 使用 OpenVINO、ONNX Runtime、TensorRT 等引擎加速推理，或直接使用 ONNX 格式模型进行推理：[高性能推理](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/inference_deployment/local_inference/high_performance_inference.html).) +- 使用多 GPU 和多进程加速推理：[流水线并行推理](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/pipeline_usage/instructions/parallel_inference.html).) +- 将 PaddleOCR 集成到 C++、C#、Java 等编写的应用中：[服务化部署](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/inference_deployment/serving/serving.html).) - -## 🧩 More Features - -- Convert models to ONNX format: [Obtaining ONNX Models](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/inference_deployment/others/obtaining_onnx_models.html). -- Accelerate inference using engines like OpenVINO, ONNX Runtime, TensorRT, or perform inference using ONNX format models: [High-Performance Inference](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/inference_deployment/local_inference/high_performance_inference.html). -- Accelerate inference using multi-GPU and multi-process: [Parallel Inference for Pipelines](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/pipeline_usage/instructions/parallel_inference.html). -- Integrate PaddleOCR into applications written in C++, C#, Java, etc.: [Serving](https://paddlepaddle.github.io/PaddleOCR/latest/en/version3.x/inference_deployment/serving/serving.html). - -## 🔄 Quick Overview of Execution Results +## 🔄 运行效果速览 ### PP-OCRv5

- PP-OCRv5 Demo + PP-OCRv5 演示

- - ### PP-StructureV3

- PP-StructureV3 Demo + PP-StructureV3 演示

@@ -206,14 +207,13 @@ For local usage, please refer to the following documentation based on your needs

- PP-StructureV3 Demo + PP-StructureV3 演示

+## ✨ 敬请期待 -## ✨ Stay Tuned - -⭐ **Star this repository to keep up with exciting updates and new releases, including powerful OCR and document parsing capabilities!** ⭐ +⭐ **给此仓库点 Star，即可持续关注精彩更新与新版本发布，包括强大的 OCR 和文档解析能力！** ⭐

@@ -221,37 +221,35 @@ For local usage, please refer to the following documentation based on your needs

- -## 👩‍👩‍👧‍👦 Community +## 👩‍👩‍👧‍👦 社区
-| PaddlePaddle WeChat official account | Join the tech discussion group | +| 飞桨微信公众号 | 加入技术讨论群 | | :---: | :---: | | | |
- -## 😃 Awesome Projects Leveraging PaddleOCR -PaddleOCR wouldn't be where it is today without its incredible community! 💗 A massive thank you to all our longtime partners, new collaborators, and everyone who's poured their passion into PaddleOCR — whether we've named you or not. Your support fuels our fire! +## 😃 基于 PaddleOCR 的优秀项目 +PaddleOCR 能取得今天的成就，离不开我们出色的社区！💗 衷心感谢所有长期合作伙伴、新加入的贡献者，以及每一位为 PaddleOCR 倾注热情的朋友——无论我们是否列出了你的名字。你们的支持是我们前进的动力！
-| Project Name | Description | +| 项目名称 | 描述 | | ------------ | ----------- | -| [Dify](https://github.com/langgenius/dify) |Production-ready platform for agentic workflow development.| -| [RAGFlow](https://github.com/infiniflow/ragflow) |RAG engine based on deep document understanding.| -| [pathway](https://github.com/pathwaycom/pathway) |Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.| -| [MinerU](https://github.com/opendatalab/MinerU) |Multi-type Document to Markdown Conversion Tool| -| [Umi-OCR](https://github.com/hiroi-sora/Umi-OCR) |Free, Open-source, Batch Offline OCR Software.| -| [cherry-studio](https://github.com/CherryHQ/cherry-studio) |A desktop client that supports for multiple LLM providers.| -| [haystack](https://github.com/deepset-ai/haystack) |AI orchestration framework to build customizable, production-ready LLM applications.| -| [OmniParser](https://github.com/microsoft/OmniParser) |OmniParser: Screen Parsing tool for Pure Vision Based GUI Agent.| -| [QAnything](https://github.com/netease-youdao/QAnything) |Question and Answer based on Anything.| -| [Learn more projects](./awesome_projects.md) | [More projects based on PaddleOCR](./awesome_projects.md)| +| [Dify](https://github.com/langgenius/dify) |面向智能体工作流开发的生产级平台。| +| [RAGFlow](https://github.com/infiniflow/ragflow) |基于深度文档理解的 RAG 引擎。| +| [pathway](https://github.com/pathwaycom/pathway) |用于流处理、实时分析、LLM 流水线和 RAG 的 Python ETL 框架。| +| [MinerU](https://github.com/opendatalab/MinerU) |多类型文档转 Markdown 工具| +| [Umi-OCR](https://github.com/hiroi-sora/Umi-OCR) |免费、开源、批量离线的 OCR 软件。| +| [cherry-studio](https://github.com/CherryHQ/cherry-studio) |支持多 LLM 提供商的桌面客户端。| +| [haystack](https://github.com/deepset-ai/haystack)|用于构建可定制、生产级 LLM 应用的 AI 编排框架。| +| [OmniParser](https://github.com/microsoft/OmniParser)|OmniParser：面向纯视觉 GUI Agent 的屏幕解析工具。| +| [QAnything](https://github.com/netease-youdao/QAnything)|基于任何内容的问答系统。| +| [了解更多项目](./awesome_projects.md) | [更多基于 PaddleOCR 的项目](./awesome_projects.md)|
-## 👩‍👩‍👧‍👦 Contributors +## 👩‍👩‍👧‍👦 贡献者
@@ -263,15 +261,14 @@ PaddleOCR wouldn't be where it is today without its incredible community! 💗 A

- Star-history + Star 历史

+## 📄 许可证 +本项目基于 [Apache 2.0 许可证](LICENSE) 发布。 -## 📄 License -This project is released under the [Apache 2.0 license](LICENSE). - -## 🎓 Citation +## 🎓 引用 ```bibtex @misc{cui2025paddleocr30technicalreport,