Spaces:
Runtime error
Runtime error
Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,51 @@
|
|
1 |
---
|
2 |
-
title:
|
3 |
-
emoji:
|
4 |
-
colorFrom:
|
5 |
colorTo: green
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 5.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: apache-2.0
|
11 |
-
|
12 |
---
|
13 |
|
14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
title: MonkeyOCR Document Parser
|
3 |
+
emoji: 🐵
|
4 |
+
colorFrom: blue
|
5 |
colorTo: green
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 5.23.3
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: apache-2.0
|
11 |
+
python_version: 3.10
|
12 |
---
|
13 |
|
14 |
+
# MonkeyOCR Document Parser
|
15 |
+
|
16 |
+
MonkeyOCR是一个轻量级的多模态文档解析模型,采用Structure-Recognition-Relation (SRR)三元组范式。
|
17 |
+
|
18 |
+
## 功能特性
|
19 |
+
|
20 |
+
- 🔍 **高精度识别**: 支持中英文文档解析
|
21 |
+
- 📊 **表格提取**: 智能识别和提取表格数据
|
22 |
+
- 🧮 **公式解析**: 准确识别数学公式
|
23 |
+
- 📝 **结构化输出**: 输出Markdown格式结果
|
24 |
+
- ⚡ **高效处理**: 0.84页/秒的处理速度
|
25 |
+
|
26 |
+
## 使用方法
|
27 |
+
|
28 |
+
1. 上传PDF文档或图片文件
|
29 |
+
2. 输入解析提示词(可选)
|
30 |
+
3. 点击"开始解析"按钮
|
31 |
+
4. 查看Markdown格式的解析结果
|
32 |
+
|
33 |
+
## 模型信息
|
34 |
+
|
35 |
+
- **参数量**: 3B
|
36 |
+
- **支持语言**: 中文、英文
|
37 |
+
- **支持格式**: PDF, PNG, JPG, JPEG
|
38 |
+
- **基础模型**: 基于Qwen2.5-VL
|
39 |
+
|
40 |
+
## 引用
|
41 |
+
|
42 |
+
```bibtex
|
43 |
+
@misc{li2025monkeyocrdocumentparsingstructurerecognitionrelation,
|
44 |
+
title={MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm},
|
45 |
+
author={Zhang Li and Yuliang Liu and Qiang Liu and Zhiyin Ma and Ziyang Zhang and Shuo Zhang and Zidun Guo and Jiarui Zhang and Xinyu Wang and Xiang Bai},
|
46 |
+
year={2025},
|
47 |
+
eprint={2506.05218},
|
48 |
+
archivePrefix={arXiv},
|
49 |
+
primaryClass={cs.CV},
|
50 |
+
url={https://arxiv.org/abs/2506.05218},
|
51 |
+
}
|