DocTR

Deep learning based OCR library in Python and TensorFlow/PyTorch.

Open SourceSelf HostedOffline Capable
0.0 (0)

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

Price
Free
Platform
Local/Desktop
Difficulty
Easy (2/5)
License
Apache-2.0
Added
Apr 3, 2026

Related Tools

One-stop tool for high-quality PDF extraction to Markdown or JSON.

Open SourceSelf HostedOffline
Easy
0.0 (0)

Python bindings for MuPDF library for fast PDF text and image extraction.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Python library for extracting text, tables, and metadata from PDFs.

Open SourceSelf HostedOffline
Beginner
0.0 (0)

Multilingual document OCR toolkit with line detection and layout analysis.

Open SourceSelf HostedOfflineGPU 4GB+
Easy
0.0 (0)

Vision-language model based OCR toolkit by AI2 for document understanding.

Open SourceSelf HostedOfflineGPU 8GB+
Intermediate
0.0 (0)

OCR tool specialized in recognizing mathematical equations and LaTeX.

Beginner
0.0 (0)
Browse all OCR & Document Processing tools