Marker
Converts PDFs to clean Markdown with high accuracy for text, tables, and equations.
About
Marker by Vik Paruchuri converts PDFs and other documents into clean Markdown, JSON, chunks, or HTML quickly and accurately, handling text, tables, LaTeX equations, and images through a pipeline of layout detection, OCR, and formatting models. A managed platform and batch service are also offered. The open-source tool is released under the GPL-3.0 license, with a separate commercial self-hosting license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- OCR & Document Processing
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- GPL-3.0
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Document parsing library by IBM for converting PDFs and documents to structured data.
Deep learning based OCR library in Python and TensorFlow/PyTorch.
One-stop tool for high-quality PDF extraction to Markdown or JSON.
Python bindings for MuPDF library for fast PDF text and image extraction.
Tool for extracting tables from PDF files into CSV or DataFrame format.
Python library for extracting tables from PDF files.