deepseek-ai/DeepSeek-OCR is an open-source model for optical character recognition, enabling extraction of text from images. It supports integration with PyTorch and Docker, making it suitable for document digitization and data extraction workflows. Designed for data scientists and developers working with scanned documents and images.
DeepSeek OCR is a Foundation models & chat project. It automates extraction of text from images for document processing and digitization. DeepSeek OCR is an open-source project aimed at data scientists. The project is open source (Open Source). It ships for the command line, and it can be self-hosted.
Behind DeepSeek OCR is deepseek-ai, and it first shipped in 2025. Key capabilities include optical character recognition, image-to-text conversion, and pyTorch support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do