Skip to content

Home

Since its initial release, PaddleOCR has gained widespread acclaim across academia, industry, and research communities, thanks to its cutting-edge algorithms and proven performance in real-world applications. Itโ€™s already powering popular open-source projects like Umi-OCR, OmniParser, MinerU, and RAGFlow, making it the go-to OCR toolkit for developers worldwide.

On May 20, 2025, the PaddlePaddle team unveiled PaddleOCR 3.0, fully compatible with the official release of the PaddlePaddle 3.0 framework. This update further boosts text-recognition accuracy, adds support for multiple text-type recognition and handwriting recognition, and meets the growing demand from large-model applications for high-precision parsing of complex documents. When combined with the ERNIE 4.5T, it significantly enhances key-information extraction accuracy. PaddleOCR 3.0 also introduces support for domestic hardware platforms such as KUNLUNXIN and Ascend.

Three Major New Features in PaddleOCR 3.0:

  • ๐Ÿ–ผ๏ธ Universal-Scene Text Recognition Model PP-OCRv5: A single model that handles five different text types plus complex handwriting. Overall recognition accuracy has increased by 13 percentage points over the previous generation.

  • ๐Ÿงฎ General Document-Parsing Solution PP-StructureV3: Delivers high-precision parsing of multi-layout, multi-scene PDFs, outperforming many open- and closed-source solutions on public benchmarks.

  • ๐Ÿ“ˆ Intelligent Document-Understanding Solution PP-ChatOCRv4: Natively powered by the WenXin large model 4.5T, achieving 15.7 percentage points higher accuracy than its predecessor.

In addition to providing an outstanding model library, PaddleOCR 3.0 also offers user-friendly tools covering model training, inference, and service deployment, so developers can rapidly bring AI applications to production.

You can Quick Start directly, find comprehensive documentation in the PaddleOCR Docs, get support via Github Issus, and explore our OCR courses on OCR courses on AIStudio.

๐Ÿ”„ Quick Overview of Execution Results

๐Ÿ‘ฉโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ Community

Comments