天枢 - 企业级 AI 数据预处理平台 | PDF/Office转Markdown | 支持MCP协议AI助手集成 | Vue3+FastAPI全栈方案
-
Updated
Oct 24, 2025 - Python
#
deepseek-ocr
Here are 4 public repositories matching this topic...
Un-LOCC: Universal Lossy Optical Context Compression for Vision-Based Language Models Achieve nearly 3x token compression at over 93% retrieval accuracy using existing Vision-Language Models.
-
Updated
Oct 24, 2025 - Python
A Windows-based screenshot OCR utility powered by DeepSeek-OCR. This tool allows users to quickly capture screen regions and perform high-accuracy Optical Character Recognition (OCR) directly on the captured image, leveraging the powerful DeepSeek-OCR model. It supports local model deployment and features real-time model output streaming.
python windows real-time ocr ai computer-vision gpu-acceleration ocr-python screenshot-tool deepseek-ocr
-
Updated
Oct 21, 2025 - Python
DeepSeek-OCR-powered snapping tool that gives you text instead of images. Convert selected screen area to markdown with a single hotkey. Screenshot OCR.
-
Updated
Oct 23, 2025 - Python
Improve this page
Add a description, image, and links to the deepseek-ocr topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the deepseek-ocr topic, visit your repo's landing page and select "manage topics."