Instructions to use PaddlePaddle/PP-OCRv6_tiny_det with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PaddleOCR
How to use PaddlePaddle/PP-OCRv6_tiny_det with PaddleOCR:
# 1. See https://www.paddlepaddle.org.cn/en/install to install paddlepaddle # 2. pip install paddleocr from paddleocr import TextDetection model = TextDetection(model_name="PP-OCRv6_tiny_det") output = model.predict(input="path/to/image.png", batch_size=1) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@ PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Ta
|
|
| 30 |
|
| 31 |
|
| 32 |
**🔥 [Official Website](https://www.paddleocr.com)**
|
| 33 |
-
**📝 [Technical Report
|
| 34 |
|
| 35 |
</div>
|
| 36 |
|
|
@@ -165,7 +165,16 @@ For details about usage command and descriptions of parameters, please refer to
|
|
| 165 |
|
| 166 |
[PaddleOCR Documentation](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html)
|
| 167 |
|
| 168 |
-
<!-- TODO: Update arxiv link when PP-OCRv6 paper is published -->
|
| 169 |
## Citation
|
| 170 |
|
| 171 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
|
| 32 |
**🔥 [Official Website](https://www.paddleocr.com)**
|
| 33 |
+
**📝 [Technical Report](https://arxiv.org/pdf/2606.13108)**
|
| 34 |
|
| 35 |
</div>
|
| 36 |
|
|
|
|
| 165 |
|
| 166 |
[PaddleOCR Documentation](https://paddlepaddle.github.io/PaddleOCR/latest/en/index.html)
|
| 167 |
|
|
|
|
| 168 |
## Citation
|
| 169 |
|
| 170 |
+
```bibtex
|
| 171 |
+
@misc{zhang2026ppocrv6,
|
| 172 |
+
title={PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks},
|
| 173 |
+
author={Yubo Zhang and Xueqing Wang and Manhui Lin and Yue Zhang and Penglongyi Deng and Ting Sun and Tingquan Gao and Zelun Zhang and Jiaxuan Liu and Changda Zhou and Hongen Liu and Suyin Liang and Cheng Cui and Yi Liu and Dianhai Yu and Yanjun Ma},
|
| 174 |
+
year={2026},
|
| 175 |
+
eprint={2606.13108},
|
| 176 |
+
archivePrefix={arXiv},
|
| 177 |
+
primaryClass={cs.CV},
|
| 178 |
+
url={https://arxiv.org/abs/2606.13108},
|
| 179 |
+
}
|
| 180 |
+
```
|