Folio-OCR

Folio-OCR is a local-first batch OCR application designed for digitizing books, scanned documents, and images. The project describes itself as a free, local alternative to ABBYY FineReader. It processes PDFs and images through layout detection and optical character recognition, outputting editable Markdown, Word, EPUB, or plain text files while preserving document structure.

The application features a three-panel editor with thumbnail navigation, real-time OCR progress tracking, and batch processing capabilities. It supports mixed uploads of PNG, JPG, GIF, BMP images and PDF files, with intelligent text region merging to reduce processing overhead. Built with FastAPI backend, Vanilla JavaScript frontend, and SQLite persistence, it runs entirely offline using Ollama and GLM-OCR models.