- Adjust the threshold for considering tables inside other tables from2 to 3
- Add support for custom formula delimiters through user configuration
- Pin pdfminer.six to version 20250324 to prevent parsing failures
- Improve formula parsing success rate for better formula rendering
- Upgrade pdfminer.six to the latest version to fix PDF parsing issues- Update changelog in both English and Chinese README files
- Add new Chinese OCR model (ch_PP-OCRv4_rec_server_doc_infer) for server-side use
- Update language support in app.py to include new Chinese model
- Modify models_config.yml to add new model configuration
- Fix lang parameter ineffectiveness during table parsing model initialization
- Resolve significant slowdown in OCR and table parsing speed in CPU mode
- Update changelog in README.md and README_zh-CN.md
- Fix lang parameter ineffectiveness during table parsing model initialization
- Resolve significant slowdown in OCR and table parsing speed in CPU mode
- Update changelog in README.md and README_zh-CN.md
- Update README.md and README_zh-CN.md with the latest changes
- Add new release notes for version 1.3.4
- Include improvements in OCR detection speed and page-level sorting
- Update version history in both English and Chinese README files
- Add note about model update required for fixing word concatenation issue- Ensure consistency between English and Chinese versions
- Update version history in README.md and README_zh-CN.md
- Add details for 1.3.2 release and previous versions
- Update Windows CUDA acceleration installation instructions
- Refactor changelog entries for better readability and organization
- Update Python version requirements to >=3.10
- Simplify torch installation command- Remove numpy version restriction
- Update CUDA compatibility information
- Adjust environment creation commands across multiple documentation files
- Remove duplicate entries for paddleocr2torch and thread safety
- Add new entry for real-time progress bar implementation
- Update mfr model to unimernet(2503)
- Extend torch version compatibility
- Enhance cuda support for various GPU models
- Improve parsing speed on MPS devices
- Update release notes in both English and Chinese README files
- Highlight major optimizations and improvements in version 1.3.0
- Clarify compatibility changes for torch, CUDA, and Python versions
- Emphasize performance improvements and parsing speed enhancements
- Mention specific bug fixes and parsing effect optimizations
- Update changelog for version 1.3.0 release
- Clarify CUDA and GPU compatibility improvements
- Add information about batch processing speed improvements
- Update model download process and memory usage optimizations
- Include link to batch processing demo script
- Add RapidOCR and PaddleOCR2Pytorch to the Acknowledgments list in README.md
- Add RapidOCR and PaddleOCR2Pytorch to the Acknowledgments list in README_zh-CN.md
- Installation and compatibility optimizations:
- Replace PaddleOCR with paddleocr2torch to resolve conflicts between Paddle and PyTorch
- Remove layoutlmv3 usage to solve compatibility issues with detectron2
- Extend PyTorch version compatibility to2.2~2.6 - Extend CUDA compatibility to 11.8~12.6
- Extend Python version compatibility to 3.10~3.12
- Performance optimizations:
- Support batch processing for multiple PDF files
- Optimize mfr model loading and usage to reduce memory consumption and improve speed
- Reduce minimum memory requirement to 6GB
- Improve running speed on MPS devices
- Parsing effect optimization:
- Update mfr model to unimernet(2503) to fix line break issues in multi-line formulas
- Update README.md and README_zh-CN.md with the latest changes
- Add details about bug fixes in version1.2.1
- Include improvements for full-width to half-width conversion, caption matching, and formula span issues
- Add information about OS and CANN version compatibility
- Include details on high-performance mode and its requirements
- Update paddlepaddle-gpu installation instructions for CUDA acceleration
- Remove unnecessary empty line from changelog
- Update English and Chinese README files with the changelog for version 1.2.0
- Include details on performance optimizations, parsing improvements, and bug fixes
- Highlight specific enhancements for PDF document classification, watermark handling, and layout matching
- Update English and Chinese README files with the changelog for version 1.2.0
- Include details on performance optimizations, parsing improvements, and bug fixes
- Highlight specific enhancements for PDF document classification, watermark handling, and layout matching
- Improve performance: optimize resource usage and processing pipeline for faster parsing on high-end devices- Enhance parsing effects: add new heading classification feature to online demo
- Refactor changelog structure for better readability and organization
- Enable table recognition by default in both English and Chinese README files
- Add MPS (Metal Performance Shaders) as an acceleration option for MacOS in the Chinese README
- Update the description of acceleration options in the Chinese README
- Added information about MPS acceleration support for Apple silicon chips- Updated README files to include MPS-related content and configuration instructions
- Improved language and formatting consistency across both English and Chinese README files
- Correct the release date for version 1.0.0 in both English and Chinese README files
- Ensure consistency across documentation for the official release
myhloli