vorojar/Folio-OCR
Batch OCR workbench powered by local GLM-OCR and Ollama models for document digitization.
Not currently ranked — collecting fresh signals.
star history
Folio-OCR is a three-panel document OCR application that uses local GLM-OCR and Ollama to recognize text from PDFs and images in batch. It performs layout detection to automatically segment pages into text regions, merges adjacent areas to reduce API calls, and exports results as Markdown, Word, EPUB, or plain text. The tool runs entirely offline with SQLite for session persistence.
Frequently asked
- What is vorojar/Folio-OCR?
- Batch OCR workbench powered by local GLM-OCR and Ollama models for document digitization.
- Is Folio-OCR open source?
- Yes — vorojar/Folio-OCR is an open-source project tracked on heatdrop.
- What language is Folio-OCR written in?
- vorojar/Folio-OCR is primarily written in Python.
- How popular is Folio-OCR?
- vorojar/Folio-OCR has 448 stars on GitHub.
- Where can I find Folio-OCR?
- vorojar/Folio-OCR is on GitHub at https://github.com/vorojar/Folio-OCR.