Stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Toolkit for linearizing PDFs for LLM datasets/training
Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.
Free English to Chinese Dictionary Database
Multilingual Document Layout Parsing in a Single Vision-Language Model
📄 Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVINO, PaddlePaddle and PyTorch.
NVDA, the free and open source Screen Reader for Microsoft Windows
Allows access math content written by MathML ; Assist writing math content by LaTeX
SentenceNav is an NVDA add-on that allows you to read text by sentences, as opposed to by paragraphs or words.
Remote Desktop Accessibility for the NVDA screen reader
This NVDA add-on watches changes to attributes of navigator objects.
A Python Interface and NVDA plugin to MathCAT
An Orca screen reader plugin that makes it communicate with NVDA Remote
clipboard enhancement add-on for nvda screen reader
An NVDA add-on to split screen reader and audio from other programs to different sound channels (add-on idea credit: Tony Malykh)
An add-on with collection of modules to improve support for Microsoft Office
generate caption for image using local model, Describe the image objects browsed by NVDA, support shortcut key recognition.Result will copy to clipboard automatically .