neosun100/DeepSeek-OCR-WebUI
A web interface for serving the DeepSeek-OCR-2 visual model for optical character recognition tasks.
Velocity · 7d
+1.9
★ / day
Trend
→steady
star history
This project provides a Vue 3 web UI for the DeepSeek-OCR-2 model, enabling image text recognition across multiple modes including batch processing. The backend runs FastAPI with PyTorch and vLLM for model inference. Users can upload images or documents for OCR extraction with real-time logging and responsive design.