v3.2.0

PaddlePaddle/PaddleOCRv3.2.0Aug 21, 2025by cuicheng01

AI Summary

Introduced PP-OCRv5 models for English, Thai, and Greek, upgraded C++ deployment capabilities, implemented fine-grained benchmarking, and separated core and optional dependencies.

Key Highlights

New PP-OCRv5 models for English (11% improvement), Thai (82.68%), and Greek (89.28%).
Full C++ deployment support for PP-OCRv5 on Linux and Windows.
High-performance inference now supports CUDA 12 with Paddle Inference or ONNX Runtime.
Separation of core and optional dependencies to reduce installation footprint.

New Features

New language models (English, Thai, Greek) for PP-OCRv5.
C++ deployment support (Linux/Windows).
CUDA 12 support for high-performance inference.
Fine-grained benchmarking tools.
Dependency separation.

Full Release Notes

## 2025.8.21 v3.2.0 released

- **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.**

- **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.

- **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.**
    - **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.**

- **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.

- **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 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.

## 2025.8.21 v3.2.0 发布

- **重要模型新增：**
    - 新增 PP-OCRv5 英文、泰文、希腊文识别模型的训练、推理、部署。**其中 PP-OCRv5 英文模型较 PP-OCRv5 主模型在英文场景提升 11%，泰文识别模型精度 82.68%，希腊文识别模型精度 89.28%。**

- **部署能力升级：**
    - **全面支持飞桨框架 3.1.0 和 3.1.1 版本。**
    - **全面升级 PP-OCRv5 C++ 本地部署方案，支持 Linux、Windows，功能及精度效果与 Python 方案保持一致。**
    - **高性能推理支持 CUDA 12，可使用 Paddle Inference、ONNX Runtime 后端推理。**
    - **高稳定性服务化部署方案全面开源，支持用户根据需求对 Docker 镜像和 SDK 进行定制化修改。**
    - 高稳定性服务化部署方案支持通过手动构造HTTP请求的方式调用，该方式允许客户端代码使用任意编程语言编写。

- **Benchmark支持**：
    - **全部产线支持产线细粒度 benchmark，能够测量产线端到端推理时间以及逐层、逐模块的耗时数据，可用于辅助产线性能分析。**
    - **文档中补充各产线常用配置在主流硬件上的关键指标，包括推理耗时和内存占用等，为用户部署提供参考。**

- **Bug修复：**
    - 修复模型训练时训练日志保存失败的问题。
    - 对公式模型的数据增强部分进行了版本兼容性升级，以适应新版本的 albumentations 依赖，并修复了在多进程使用 tokenizers 依赖包时出现的死锁警告。
    - 修复 PP-StructureV3 配置文件中的 `use_chart_parsing` 等开关行为与其他产线不统一的问题。

- **其他升级：**
    - **分离必要依赖与可选依赖。使用基础文字识别功能时，仅需安装少量核心依赖；若需文档解析、信息抽取等功能，用户可按需选择安装额外依赖。**
    - **支持 Windows 用户使用英伟达 50 系显卡，可根据安装文档安装对应版本的 paddle 框架。**
    - **PP-OCR 系列模型支持返回单文字坐标。**
    - 模型新增 AIStudio、ModelScope 等下载源。可指定相关下载源下载对应的模型。
    - 支持图表转表 PP-Chart2Table 单功能模块推理能力。
    - 优化部分使用文档中的描述，提升易用性。
    
## New Contributors
* @awkrail made their first contribution in https://github.com/PaddlePaddle/PaddleOCR/pull/16262
* @liuwake made their first contribution in https://github.com/PaddlePaddle/PaddleOCR/pull/16281

**Full Changelog**: https://github.com/PaddlePaddle/PaddleOCR/compare/v3.1.1...v3.2.0