A real-time Electron-based desktop GUI for DeepSeek-OCR

Unaffiliated with DeepSeek

• 🌐 Web Access: Use from any device on your local network (new!)
• Drag-and-drop image upload
• Real-time OCR processing

• Click regions to copy
• Export results as ZIP with markdown images
• GPU acceleration (CUDA)

• Windows 10/11, other OS are experimental
• Node.js 18+ (download)
• Python 3.12+ (download)
• NVIDIA GPU with CUDA

1. Extract the ZIP file
2. Run start-client.bat
   • First run will automatically install dependencies.
   • Subsequent runs will start quicker.
3. Load Model - Click the "Load Model" button in the app, this will download or load the model.
   • If this is the first run, this might take some time.
4. Drop an image or click the drop zone to select one.
5. Run OCR - Click "Run OCR" to process.

Note: if you have issues processing images but the model loads properly, please close and re-open the app and try with the default resolution for "base" and "size". This is a known issue, if you can help to fix it I would appreciate it!

New Feature: The Flask server now serves the entire client interface on your local network!

You can access the OCR client from any device on your network (phone, tablet, another computer) without installing the Electron app.

1. Start the server on your main machine:

   python start.py

2. Find your server's IP address:

   • Windows: ipconfig
   • Linux/macOS: ip addr or ifconfig

3. Access from any device on your network:

   http://[YOUR-SERVER-IP]:5000
   

   Example: http://192.168.1.100:5000

• Full OCR functionality in the browser
• No Electron installation needed on client devices
• Drag-and-drop image upload works in the browser
• All processing happens on the server
• Perfect for using from mobile devices or remote machines

Note: The server runs on 0.0.0.0:5000 to accept connections from any device on your local network. Make sure your firewall allows incoming connections on port 5000.

Note: Linux and macOS have not been tested yet. Use start-client.sh instead of start-client.bat.

PRs welcome! If you test on Linux/macOS and encounter issues, please open a pull request with fixes.

• Model HuggingFace
• Model Blog Post
• Model GitHub

• Code cleanup needed (quickly put together)
• TypeScript
• Updater from GitHub releases
• PDF support
• Batch processing
• CPU support?
• Web version (so you can run the server on a different machine) ✅ Implemented!
• Better progress bar algo
• ???

MIT