| library_name: onnx | |
| tags: | |
| - ocr | |
| - paddleocr | |
| - pp-ocrv6 | |
| - text-detection | |
| - onnx | |
| - inference4j | |
| license: apache-2.0 | |
| pipeline_tag: object-detection | |
| # PP-OCRv6 Tiny Det — ONNX | |
| ONNX export of [PaddlePaddle/PP-OCRv6_tiny_det_onnx](https://huggingface.co/PaddlePaddle/PP-OCRv6_tiny_det_onnx), the lightweight tiny text detection model from PaddleOCR PP-OCRv6 (~1.8 MB). Designed for resource-constrained environments. | |
| Mirrored for use with [inference4j](https://github.com/inference4j/inference4j), an inference-only AI library for Java. | |
| ## Original Source | |
| - **Repository:** [PaddlePaddle](https://huggingface.co/PaddlePaddle/PP-OCRv6_tiny_det_onnx) | |
| - **License:** apache-2.0 | |
| ## Usage with inference4j | |
| ```java | |
| try (var ocr = OcrPipeline.builder().build()) { | |
| List<TextRegion> lines = ocr.read(image); | |
| } | |
| ``` | |
| ## Model Details | |
| | Property | Value | | |
| |----------|-------| | |
| | Architecture | PP-OCRv6 Tiny Detection (DBNet) | | |
| | Task | Text detection | | |
| | Model size | ~1.8 MB | | |
| | Input format | [batch, 3, H, W] (BGR, dynamic shape) | | |
| | Original framework | PaddlePaddle (PP-OCRv6) | | |
| | Technical report | [PP-OCRv6](https://github.com/PaddlePaddle/PaddleOCR) | | |
| ## License | |
| This model is licensed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0). Original model by [PaddlePaddle](https://github.com/PaddlePaddle/PaddleOCR). | |