---
license: apache-2.0
tags:
- onnx
- paddleocr
- ocr
- computer-vision
- text-recognition
- text-detection
library_name: onnxruntime
pipeline_tag: image-to-text
base_model: 
- PaddlePaddle/PP-OCRv5_server_det
- PaddlePaddle/PP-OCRv5_server_rec
---

# PaddleOCR ONNX Models

PaddleOCR PP-OCRv5 models converted to ONNX format for efficient OCR inference.

[English](#english) | [中文說明](#中文說明)

## 中文說明

這是 PaddleOCR PP-OCRv5 模型的 ONNX 格式版本，用於高效率的文字辨識推理。

### 模型檔案說明

| 檔案名稱 | 說明 |
|---------|------|
| `PP-OCRv5_server_det_infer.onnx` | 文字檢測模型 - 偵測圖片中文字的位置 |
| `PP-OCRv5_server_rec_infer.onnx` | 文字辨識模型 - 辨識文字內容 |
| `PP-LCNet_x1_0_textline_ori_infer.onnx` | 文字方向分類模型 |
| `PP-LCNet_x1_0_doc_ori_infer.onnx` | 文件方向修正模型 |
| `UVDoc_infer.onnx` | 文件展平模型 |
| `PP-OCRv5_server_rec_infer.yml` | 字符字典配置檔 |

### 快速使用

```python
from huggingface_hub import hf_hub_download

# 下載文字檢測模型
det_model_path = hf_hub_download(
    repo_id="marsena/paddleocr-onnx-models",
    filename="PP-OCRv5_server_det_infer.onnx"
)

# 下載文字辨識模型  
rec_model_path = hf_hub_download(
    repo_id="marsena/paddleocr-onnx-models",
    filename="PP-OCRv5_server_rec_infer.onnx"
)
```

### 一次下載所有模型

```python
from huggingface_hub import snapshot_download

# 下載所有模型檔案到本地資料夾
snapshot_download(
    repo_id="marsena/paddleocr-onnx-models",
    local_dir="./paddleocr_onnx"
)
```

### 支援的語言和文字類型

- **語言支援**: 簡體中文、繁體中文、英文、日文
- **文字類型**: 印刷體、手寫體、直書文字、旋轉文字、彎曲文字
- **輸入格式**: 圖片檔案 (JPEG, PNG)
- **運行環境**: 支援 CPU 和 GPU 推理

---

## English

## Model Files

| File | Description |
|------|-------------|
| `PP-OCRv5_server_det_infer.onnx` | Text detection model |
| `PP-OCRv5_server_rec_infer.onnx` | Text recognition model |
| `PP-LCNet_x1_0_textline_ori_infer.onnx` | Text orientation classification |
| `PP-LCNet_x1_0_doc_ori_infer.onnx` | Document orientation correction |
| `UVDoc_infer.onnx` | Document unwarping |
| `PP-OCRv5_server_rec_infer.yml` | Character dictionary config |

## Source Models

These ONNX models are converted from official PaddlePaddle PP-OCRv5 models:

- **Detection Model**: [PaddlePaddle/PP-OCRv5_server_det](https://huggingface.co/PaddlePaddle/PP-OCRv5_server_det)
- **Recognition Model**: [PaddlePaddle/PP-OCRv5_server_rec](https://huggingface.co/PaddlePaddle/PP-OCRv5_server_rec)
- **Official Documentation**: [PP-OCRv5 Introduction](https://paddlepaddle.github.io/PaddleOCR/main/en/version3.x/algorithm/PP-OCRv5/PP-OCRv5.html)

## Usage

### Download Specific Model

```python
from huggingface_hub import hf_hub_download

# Download detection model
det_model_path = hf_hub_download(
    repo_id="marsena/paddleocr-onnx-models",
    filename="PP-OCRv5_server_det_infer.onnx"
)

# Download recognition model  
rec_model_path = hf_hub_download(
    repo_id="marsena/paddleocr-onnx-models",
    filename="PP-OCRv5_server_rec_infer.onnx"
)
```

### Download All Models

```python
from huggingface_hub import snapshot_download

# Download all model files to local directory
snapshot_download(
    repo_id="marsena/paddleocr-onnx-models",
    local_dir="./paddleocr_onnx"
)
```

### ONNX Runtime Inference

```python
import onnxruntime as ort
import numpy as np

# Load model
session = ort.InferenceSession("PP-OCRv5_server_det_infer.onnx")

# Run inference
input_name = session.get_inputs()[0].name
output = session.run(None, {input_name: input_data})
```

## Model Specifications

- **Languages**: Simplified Chinese, Traditional Chinese, English, Japanese
- **Text Types**: Printed text, handwriting, vertical text, rotated text
- **Input Format**: Images (JPEG, PNG)
- **Output Format**: Bounding boxes + recognized text
- **Runtime**: ONNX Runtime 1.16+
- **Hardware**: CPU and GPU inference supported

## License

These models follow the **Apache License 2.0**, consistent with the original PaddleOCR project.

- **PaddleOCR Repository**: https://github.com/PaddlePaddle/PaddleOCR
- **License Details**: [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)

## Conversion Information

- **Conversion Tool**: Paddle2ONNX
- **ONNX Version**: 1.12+
- **Source Framework**: PaddlePaddle 2.5+
- **Conversion Date**: January 2025

## Citation

If you use these models in your research, please cite the original PaddleOCR paper:

```bibtex
@misc{paddleocr2020,
    title={PaddleOCR: Awesome multilingual OCR toolkits},
    author={PaddlePaddle Authors},
    howpublished = {\url{https://github.com/PaddlePaddle/PaddleOCR}},
    year={2020}
}
```

## Issues

For model usage issues, please report to the original PaddleOCR repository:
- **PaddleOCR Issues**: https://github.com/PaddlePaddle/PaddleOCR/issues