PP-OCRv5 Server Rec
PaddlePaddle/PP-OCRv5_server_rec
published Jun 2025 · updated Jul 2025
PP-OCRv5 Server Rec is an image-to-text model that recognizes text from images, supporting Simplified Chinese, Traditional Chinese, English, Japanese, and complex scenarios such as handwriting, vertical text, pinyin, and rare characters using a single model.
specs
| Task | Image-to-Text (Text Recognition) |
| Architecture | PP-OCRv5 server recognition model |
| Average Accuracy | 0.8401 (line-level over 12 scenarios) |
about this model
| Scenario | Accuracy |
|---|---|
| Handwritten Chinese | 0.5807 |
| Handwritten English | 0.5806 |
| Printed Chinese | 0.9013 |
| Printed English | 0.8679 |
| Traditional Chinese | 0.7472 |
| Ancient Text | 0.6039 |
| Japanese | 0.7372 |
| General Scenario | 0.5946 |
| Pinyin | 0.8384 |
| Rotation | 0.7435 |
| Distortion | 0.9314 |
| Artistic Text | 0.6397 |
This model is hosted on gigarouter as a managed, OpenAI-compatible API, providing reliable image-to-text inference without local installation.best for
- ·Text recognition in printed Chinese and English documents
- ·Handwriting recognition in Chinese and English
- ·Multilingual OCR covering Japanese and Traditional Chinese
- ·Complex scenarios like distorted, artistic, or rotated text
FAQ
It supports Simplified Chinese, Traditional Chinese, English, Japanese, as well as handwriting, vertical text, pinyin, and rare characters.
It achieves an average line-level accuracy of 0.8401 across 12 scenarios, including printed, handwritten, and distorted text.
Use the gigarouter OpenAI-compatible endpoint with an API key. Input an image and receive recognized text as the response.
The model accepts image URLs or local image files. In the pipeline, it processes cropped text-line images.
Yes, it can be used standalone for text recognition or as part of the PP-OCRv5 pipeline that includes detection and orientation modules.
We're benchmarking and onboarding PP-OCRv5 Server Rec as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.