Folio-OCR
An open-source batch OCR workbench built around Ollama and GLM-OCR, positioned as a free, local alternative to ABBYY FineReader for digitizing scanned books, documents and forms with a three-panel editor.
Folio-OCR converts scanned PDFs, book photos, exam papers and document images into batch-editable text, using PP-DocLayoutV3 for layout detection and GLM-OCR through Ollama for the visual OCR step, then merges adjacent text regions to cut the number of OCR calls. It accepts PNG, JPG, GIF, BMP and PDF input, mixed in a single batch, and runs entirely locally so documents do not need to be uploaded to a third-party OCR service.
A three-panel layout shows page thumbnails, the image preview and the OCR result, with edit and preview modes, paragraph reflow to rejoin lines broken by line wraps, full-text search across pages, and layout regions that highlight in both directions between the image and the text. Results export to Markdown, plain text, Word (.docx) and EPUB, and are kept in a SQLite database so documents and edits survive a restart.
It installs with uvx or pipx directly from its GitHub repository, or through Docker Compose alongside Ollama, with optional GPU acceleration.