models / image-to-text · coming soon
PP-OCRv5_server_det
PaddlePaddle/PP-OCRv5_server_det
A popular open image-to-text model, with 587.3K downloads a month. gigarouter benchmarks and hosts it as an OpenAI-compatible API.
status
coming soon
API providers
0
downloads / mo
587.3K
license
apache-2.0
about this model
PP-OCRv5_server_det is a text detection model that identifies text regions in images, supporting a wide range of scenarios including handwriting, vertical, rotated, and curved text across multiple languages such as Simplified Chinese, Traditional Chinese, English, and Japanese. It is part of the PP-OCRv5 series developed by the PaddleOCR team and is designed for high-performance applications.
Key Strengths
- Robust detection of text in complex layouts, varying text sizes, and challenging backgrounds.
- Handles diverse text types: handwritten, printed, artistic, distorted, and ancient text.
- Supports multiple languages and text orientations.
Recommended Use Cases
- Document analysis and digitization
- License plate recognition
- Scene text detection (e.g., signs, labels)
Accuracy Metrics
| Handwritten Chinese | Handwritten English | Printed Chinese | Printed English | Traditional Chinese | Ancient Text | Japanese | General Scenario | Pinyin | Rotation | Distortion | Artistic Text | Average |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.803 | 0.841 | 0.945 | 0.917 | 0.815 | 0 |
not yet live
We're benchmarking and onboarding PP-OCRv5_server_det 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.