doctr
A Python OCR library that extracts text from PDFs and images by detecting words and recognizing their characters. Use it to add document text extraction to an application.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
docTR is a Python library for extracting text from documents with deep-learning OCR. It uses a two-stage pipeline: a detection model locates words, then a recognition model reads them. The library accepts PDFs and images, and can also load webpages when the required dependency is installed. Users choose detection and recognition architectures, run a pretrained predictor on a document, and use the resulting text and layout information in their applications.
Key features
- Detects word locations and recognizes their text in a two-stage OCR pipeline
- Lets users select detection and recognition model architectures
- Loads PDFs and images, with webpage input available when its dependency is installed
- Can detect document layout as part of the OCR pipeline
Best for
Developers who need deep-learning OCR to extract text from document PDFs or images. It is also useful when an application needs selectable OCR models or document layout detection.
- Upstream
- mindee/doctr
- Fork on GitHub
- Guo-astro/doctr
- Upstream stars
- 6.4k
- Category
- Documents, media and content
- Language
- Python
- License
- Apache-2.0
- Forked
- 2026-10-05
- Sync status
- In syncLast synced 2026-11-08
More in Documents, media and content
LuxTTS is a lightweight text-to-speech model for cloning a voice from reference audio and generating clear 48 kHz speech. Use it locally through Python, Colab, or Hugging Face Spaces.
Forked 2026-10-19Last synced 2026-11-08License: Apache-2.0Documents, media and contentGitHub
A self-hosted knowledge base for writing, organizing, searching, and sharing Markdown notes. It supports offline access and team workspaces for personal or collaborative documentation.
Forked 2026-10-19Last synced 2026-11-08License: MITDocuments, media and contentGitHub
Textus is a free, open-source Markdown editor with an AI writing assistant for drafting and editing on macOS, Windows, and Linux.
Forked 2026-10-18Last synced 2026-11-08License: MITDocuments, media and contentGitHub
Clypra is a free, open-source video editor for editing and arranging footage on a frame-accurate timeline. It uses Rust and GPU acceleration for video decoding and rendering.
Forked 2026-10-14Last synced 2026-11-08License: MITDocuments, media and contentGitHub