v3.5.0
deepseek-ai/DeepSeek-Coder-V2v3.5.0Apr 21, 2026by Bobholamovic
AI Summary
This release marks a deep integration with the Hugging Face ecosystem, supporting 20 major models and offering new document conversion capabilities. It also introduces a browser-based inference SDK for running OCR models directly in the web environment.
Key Highlights
- Deep integration with Hugging Face ecosystem
- Document format conversion (Word/Excel/PPT to Markdown)
- PaddleOCR.js browser SDK
- DOCX export for PP-StructureV3
- 20 major models supporting Transformers backend
New Features
- Hugging Face integration
- Document conversion
- Browser SDK
- DOCX export
Full Release Notes
## 2026.4.21 v3.5.0 released * Deeply integrated with the Hugging Face ecosystem, with 20 major models supporting Transformers as the inference backend. Supports flexible switching of inference engines, including PaddlePaddle static graph, PaddlePaddle dynamic graph, or Transformers. * Supports conversion of common document formats (Word, Excel, Powerpoint) to Markdown. * The PaddleOCR-VL series, PP-StructureV3, and PP-DocTranslation support exporting parsing results to DOCX format, making it convenient to view and edit in Word. * Official browser inference SDK PaddleOCR.js is released, supporting running PP-OCRv5 in the browser. ## 2026.4.21 v3.5.0 发布 * 深度适配 Hugging Face 生态,20 个主要模型支持以 Transformers 作为推理后端。支持灵活切换推理引擎,可选飞桨静态图、飞桨动态图或 Transformers。 * 支持常见文档格式(Word、Excel、Powerpoint)转 Markdown。 * PaddleOCR-VL 系列、PP-StructureV3、PP-DocTranslation 支持将解析结果导出为 DOCX 格式,便于在 Word 中查看和编辑。 * 发布官方浏览器推理 SDK PaddleOCR.js,支持在浏览器中运行 PP-OCRv5。 **Full Changelog**: https://github.com/PaddlePaddle/PaddleOCR/compare/v3.4.1...v3.5.0