doctr
by mindee (organization)
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k. (description from the project’s GitHub page)
Repository facts
- Stars
- 6,390
- Forks
- 687
- Open issues and pull requests
- 24
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- mindee · Organization
- Created
- Jan 8, 2021
- Last push
- Oct 16, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,919: AlibabaResearch/AdvancedLiterateMachinery
A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi La…
1,833 starsC++Apache-2.0Last push Mar 17, 2026
Rank 774: zyddnys/manga-image-translator
Translate manga/image 一键翻译各类图片内文字 https://cotrans.touhou.ai/ (no longer working)
10,513 starsPythonGPL-3.0Last push Oct 11, 2026
Rank 1,692: open-mmlab/mmocr
OpenMMLab Text Detection, Recognition and Understanding Toolbox
4,750 starsPythonApache-2.0Last push Nov 27, 2024
Rank 7,428: baudm/parseq
Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)
744 starsPythonApache-2.0Last push May 29, 2024
Rank 5,618: aiptimizer/TurboOCR
TurboOCR, >200 img/s OmnidocBench. TensorRT FP16, PP-OCRv6, HTTP + gRPC
1,136 starsC++MITLast push Sep 27, 2026
Rank 263: JaidedAI/EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
30,084 starsPythonApache-2.0Last push Dec 5, 2025