Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
| Date | Stars |
|---|---|
| 2026-07-24 | 1836 |
| 2026-07-25 | 1836 |
| 2026-07-28 | 1836 |
| 2026-07-30 | 1836 |
| 2026-07-31 | 1838 |
| 2026-08-06 | 1841 |
Today
+3 stars today
This week
+5 stars this week
This month
— stars this month
Momentum
17.0
growth rate 0.27%/day
# OnnxOCR
If this project helps you, please consider giving it a **Star**.
**A high-performance multilingual OCR project based on ONNXRuntime**
English | [简体中文](./Readme_cn.md) | [日本語](./Readme_ja.md)
## Version Updates
- **2026.05.27**
1. Added a new OCR + Qwen3.5-2B ONNX information-extraction workflow.
2. Added `onnxocr.qwen35_2b` as the package-level Qwen3.5-2B ONNX download, verification, and pure Python inference module.
3. Added `examples/id_card_extract_with_qwen.py` as an end-to-end example: OnnxOCR full-text recognition first, then Qwen3.5-2B extracts structured ID-card fields.
4. Qwen3.5-2B ONNX uses a dedicated ModelScope repository: [supersong/qwen2bonnx](https://www.modelscope.cn/models/supersong/qwen2bonnx/tree/master/models).
- **2026.05.01**
1. Added ONNX license plate detection and recognition.
2. Added RapidTable-based ONNX table recognition.
3. Added RapidLayout-based Chinese and English layout analysis.
4. Added RapidDoc-based document layout analysis and Markdown export.
5. Added `/plate`, `/table`, `/layout`, `/layout_markdown`, and related HTTP endpoints.
- **2025.05.21**
1. Added PP-OCRv5 models, supporting Simplified Chinese, Traditional Chinese, Chinese Pinyin, English, and Japanese in one model.
2. Improved overall recognition accuracy compared with PP-OCRv4.
3. Recognition accuracy is consistent with PaddleOCR 3.0.
## Core Advantages
1. **Deep learning framework free**: a general OCR project ready for deployment.
2. **Cross-architecture support**: PaddleOCR-converted ONNX models can run on ARM and x86 devices.
3. **Unified inference engine**: all ONNX models create ONNXRuntime sessions through `onnxocr/inference_engine.py`.
4. **Multilingual support**: one model supports 5 text types.
5. **Source-level integration**: `rapid_layout`, `rapid_table`, and `rapid_doc` live under the `onnxocr/` package, with no dependency on `rapidocr==3.4.3` or `rapid-orientation`.
6. **Hardware adaptation friendly**: downstream vendors can adapt GPU/NPU providers by modifying the unified inference engine.
## Environment Setup
```bash
python>=3.8
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple -r requirements.txt
```
Notes:
- By default, the repository only includes the PP-OCRv5 general OCR model files required by `tests/test_general_ocr.py`.
- Extra models for license plate recognition, table recognition, layout analysis, orientation classification, and RapidDoc Markdown export are large and should be downloaded on demand. For international users, [HuggingFace](https://huggingface.co/jingsongliu/onnxocr_model/tree/main) is recommended.
- Larger PP-OCRv5 Server ONNX models can also be downloaded separately and used to replace det/rec models under `onnxocr/models/ppocrv5/`.
## Model Download
Extra models are hosted on [HuggingFace: jingsongliu/onnxocr_model](https://huggingface.co/jingsongliu/onnxocr_model/tree/main). International users are recommended to download from HuggingFace:
```bash
python scripts/download_models.py --source huggingface
```
The core HuggingFace API is:
```python
from huggingface_hub import snapshot_download
model_dir = snapshot_download("jingsongliu/onnxocr_model")
```
For users in mainland China, ModelScope remains the default and recommended source:
```bash
python scripts/download_models.py
```
ModelScope repository: [supersong/onnxocr_model](https://www.modelscope.cn/models/supersong/onnxocr_model/tree/master/models).
The script copies the repository `models/` directory into local `onnxocr/mExcerpt of 17,125 characters
Read on GitHub
41
5
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:359c9634546817d5, topic:ocr, desc:ocr, readme:ocr
matched fp:359c9634546817d5, topic:onnxruntime, readme:inference engine