Release v3.1.1

🐛 Bug Fixes

• (rapidocr) fixed typos of directml and npu by @SWHL in cec934a

🎉 Contributors

• @SWHL

Full Changelog: 3.1.1

Release v3.1.0

🚀 Features

• adapt PR #451 by @SWHL in 41d5824
• adapt CANN of onnxruntime (PR #428) (#447) by @SWHL in d5b0738

🐛 Bug Fixes

• (rapidocr) fixed issue #438 by @SWHL in 854a46b
• (rapidocr) 添加对空文本的检查和对txt_len为0的保护 (#443) by @narcissus in f40638d
• (rapidoicr) fixed issue #446 (#453) by @SWHL in 0190646

📚 Documentation

• update README by @SWHL in f9dc678

🧪 Testing

• add unit testings of issue 440 (#445) by @SWHL in dcbe0d7

⚙️ Miscellaneous Tasks

• (rapidocr) update url of model by @SWHL in e06d51f

🎉 Contributors

• @SWHL
• @narc1ssus1

Full Changelog: 3.1.0

Release v3.0.0

🚀 Features

• support PP-OCRv5 (#437) by @SWHL in 5f86f51

🐛 Bug Fixes

• (rapidocr) fix error of importing attr by @SWHL in 123a129

⚙️ Miscellaneous Tasks

• (rapidocr_api) deleting legacy files by @SWHL in b1e92f3
• (rapidocr_api) move rapidocr_api to independent repo by @SWHL in 395d30a

🎉 Contributors

• @SWHL

Full Changelog: 3.0.0

Release v2.1.0

🚀 Features

• (rapidocr) integrated PP-OCRv4_dervr_rec-doc model (#426) by @SWHL in 80c72f5. See link for details.

• (return_word_box) support word box of English and number text (#423) by @SWHL in 5776a55

  

  

🐛 Bug Fixes

• (rapidocr) fixed logic atty of downloading file by @SWHL in 68d15c0

🧪 Testing

• (rapidocr) update tests of ch_doc_server by @SWHL in 4d35ed2

⚙️ Miscellaneous Tasks

• update demo code by @SWHL in 0ab091c

🎉 Contributors

• @SWHL

Full Changelog: 2.1.0

Release v2.0.7

🚀 Features

• (rapidocr) add whether is an interactivate window by @SWHL in 421e734
• (rapidocr) add colorlog by @SWHL in 5380806

🐛 Bug Fixes

• (rapidocr) fixed missing dict by @ok-oldking in 2d9862b
• (rapidocr) fixed sha256 error by @SWHL in 30b2d64
• (rapidocr) fixed path error of infernce engine when customizing incoming parameters by @SWHL in b2dd2db
• (rapidocr) fixed path error of infernce engine when customizing incoming parameters by @SWHL in a87ecab
• (rapidocr) fixed issue #405 (#406) by @Elwin in a8ea87c
• (rapidocr) fixed issue #394 (#411) by @SWHL in fbaaaba

📚 Documentation

• update online demo link by @SWHL in 6fce7c8

⚙️ Miscellaneous Tasks

• (rapidocr) add dict txt to package by @SWHL in 717a0ad

👏 Contrubutors

• @hzhaoy made their first contribution in #406

Full Changelog: 2.0.7

Release v2.0.6

🐛 Bug Fixes

• (rapidocr) Fix invalid classifier
• (rapidocr) Fixed issue #381 #377 (#384) (解除python 3.13限制和解除默认安装ONNXRuntime)

📚 Documentation

• Update quickstart command

Release v2.0.5

🚀 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

Release v2.0.4

🚀 Features

• (rapidocr) Support to other language ocr and update visualization (#369) by @SWHL in #369

🐛 Bug Fixes

• (rapidocr) Fixed windows 2022Server parse int exception (#366) by @ok-oldking in #366
• (rapidocr) Support gpu_id when using torch (#363)

📚 Documentation

• Fixed usage error of README
• Update use

🧪 Testing

• (rapidocr) Update vis unit tests

Release v2.0.2

🚀 Features

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

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

📚 Documentation

• Update README

Bump! Release rapidocr v2.0.1

⚠️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

• 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。
• 支持torch版本作为推理引擎
• 与PaddleOCR参数部分对齐
• 整理模型到modelscope，纳入版本管理，相应模型自动下载对齐
• 采用dataclass类来封装函数返回值，简化使用
• 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
• 文档添加版本管理 → RapidOCR Doc，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: v2.0.0...v2.0.1