DocTR
Deep learning based OCR library in Python and TensorFlow/PyTorch.
About
docTR by Mindee is an optical character recognition library for Python built on TensorFlow and PyTorch. It splits OCR into a text detection stage that localizes words and a recognition stage that reads them, shipping pretrained models for both plus end-to-end predictor wrappers. It handles documents and natural images and exports structured results with word positions. Released under the Apache 2.0 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
- Apache-2.0
- Added
- Apr 3, 2026
Related Tools
Document parsing library by IBM for converting PDFs and documents to structured data.
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.
Ready-to-use OCR library supporting 80+ languages with simple Python API.
Python library for extracting tables from PDF files.