In daily office work and development, we often need to extract text from specific regions of a large number of PDF files (e.g., dates/amounts on invoices, key indicators on reports) or capture ...
Windows-focused fork of Typhoon OCR. Gradio demo for PDF/image OCR to Markdown/HTML with layout & table extraction. Uses OpenAI-compatible API or vLLM via WSL2. A Python utility for merging multiple ...