Jackxy11 commited on
Commit
fd5d634
·
verified ·
1 Parent(s): acef6d0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -6
README.md CHANGED
@@ -1,14 +1,51 @@
1
  ---
2
- title: Monkeyocr Demo
3
- emoji: 🏢
4
- colorFrom: green
5
  colorTo: green
6
  sdk: gradio
7
- sdk_version: 5.34.0
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
11
- short_description: monkeyocr-demo
12
  ---
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }