Rapidocr

🚀 Features

- *(rapidocr)* Sup more lang model for torch inference (374)

🐛 Bug Fixes

- *(rapidocr)* Fix typos
- *(rapidocr)* Fixed issue 375
- *(vis_result)* Support to download direct font file
- *(rapidocr)* Use build number 18362 to determine whether to use dml (373)
- *(rapidocr)* Fixed key error of torch det model
- *(rapidocr)* Fix image path error of visualizing single words

⚙️ Miscellaneous Tasks

- *(rapidocr)* Optimize vis class
- *(rapidocr)* Optimize vis class

🚀 Features

- *(rapidocr)* Support to other language ocr and update visualization (369) by SWHL in https://github.com/RapidAI/RapidOCR/pull/369

🐛 Bug Fixes

- *(rapidocr)* Fixed windows 2022Server parse int exception (366) by ok-oldking in https://github.com/RapidAI/RapidOCR/pull/366
- *(rapidocr)* Support gpu_id when using torch (363)

📚 Documentation

- Fixed usage error of README
- Update use

🧪 Testing

- *(rapidocr)* Update vis unit tests

🚀 Features

*(rapidocr)* Support img url as input and optimize vis (356)

bash
rapidocr -img "https://github.com/RapidAI/RapidOCR/blob/main/python/tests/test_files/ch_en_num.jpg?raw=true" --vis_res



📚 Documentation

- Update README

⚠️注意：该版本不与`rapidocr_onnxruntime<=1.4.4`兼容。遵循语义化版本号规则，请谨慎使用，以免出现各种问题。

更新要点
- [x] 发布`rapidocr`库，整合`onnxruntime`、`openvino`、`torch`和`paddlepaddle`四个推理引擎，大家可按需安装对应的推理引擎来使用。
- [x] 支持torch版本作为推理引擎
- [x] 与PaddleOCR参数部分对齐
- [x] 整理模型到modelscope，纳入版本管理，相应模型自动下载对齐
- [x] 采用dataclass类来封装函数返回值，简化使用
- [x] 优化输入配置文件，保证可以通过配置文件使用，便于分享参数设置
- [x] 文档添加版本管理 → [RapidOCR Doc](https://rapidai.github.io/RapidOCRDocs/main/)，尚未来得及完善，doing

更新主要想法
- 考虑到终端命令行使用有限，且维护有些繁琐，新版本会弱化终端部分代码，仅保留快速验证代码。


进度：

- 2025-03-09: 完善参数校验和自动化发版流程，发布`rapidocr==2.0.1`
- 2025-03-05: 添加文档版本管理，为后续编写v2.0.0文档做准备
- 2025-03-04: 优化调用默认server模型代码，通过添加`lang_det`和`lang_rec`来实现。至此基本功能均已经实现。
- 2025-02-18: 整理pytorch版本到rapidocr中；添加自动下载字体文件功能；添加对命令行执行的单元测试
- 2025-02-14: 完善各个引擎下模型自动下载并调用功能
- 2025-02-13: 优化logger，解决重复输出问题
- 2025-02-12: 添加已有模型的自动下载功能
- 2025-02-11: 优化初始化RapidOCR传参问题
- 2025-02-10: 采用抽象基类，统一四个推理引擎代码接口
- 2025-02-08：
- 将PP-OCRv4所有模型均转换并托管在modelscope上
- 将推理引擎部分单独出来，声明基类，统一不同模态间的调用方式

相关issue 329

**Full Changelog**: https://github.com/RapidAI/RapidOCR/compare/v2.0.0...v2.0.1

常规更新，去掉无效代码

🚀 Features

- Support det mean and std config (312)
- *(rapidocr_api)* Add uvicorn timestamp
- *(rapidocr_api)* 为uvicorn日志添加时间戳 (309)

🐛 Bug Fixes

- *(rapidocr_api)* 补充依赖，指定版本号 (305)
- *(rapidocr_openvino)* Merge PR 293 294
- *(rapidocr_paddle)* Merge PR 293 294

⚙️ Miscellaneous Tasks

- *(rapidocr_paddle)* Update paddpaddle version
- Update python version
- Optimize code
- Update modelscope online demo link
- *(rapidocr_api)* Update python version
- Remove the stale issue bot

New Contributors
* imweijh made their first contribution in https://github.com/RapidAI/RapidOCR/pull/305

**Full Changelog**: https://github.com/RapidAI/RapidOCR/compare/v1.4.3...v1.4.4

What's Changed
* 优化单字符坐标及返回单字符置信度 by jesse01 in https://github.com/RapidAI/RapidOCR/pull/293
* fix: ensure 4 point for char box rec by Joker1212 in https://github.com/RapidAI/RapidOCR/pull/294

New Contributors
* jesse01 made their first contribution in https://github.com/RapidAI/RapidOCR/pull/293

**Full Changelog**: https://github.com/RapidAI/RapidOCR/compare/v1.4.2...v1.4.3