#1313th of 13 in Data and scraping for AI
easyocr
Python OCR library for text detection and recognition in 80+ languages
Live demo ↗
(opens in a new tab)Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 30.1k
- License
- Apache-2.0
- Last commit
- Dec 2025
- Last release
- Sep 2024
- Language
- Python
28,927 on 25 Mar 202630,065 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
EasyOCR is a Python package that detects text regions with the CRAFT model and reads them with a CRNN recognizer, built on PyTorch. It returns bounding boxes, text and confidence scores from file paths, URLs, bytes or numpy arrays, and also has a CLI. Model weights download automatically per language, and it runs on GPU or CPU.
Who it is for: Python developers adding OCR to apps or document pipelines
Strengths
- Two-line Python API returns boxes, text and confidence from paths, URLs, bytes or arrays
- 80+ languages across Latin, Chinese, Arabic, Devanagari and Cyrillic scripts
- CPU-only mode via gpu=False; also ships a command-line tool
- Documents custom recognition and CRAFT detection model training
Weaknesses
- Not every language combination works together in one Reader; English works with all
- Handwritten text support is listed as upcoming, not available
- Last release 1.7.2 was September 2024
- Issues older than 6 months are auto-closed; maintainers cite limited resources
What it needs
- GPU optional
- Docker
- Needs PyTorch, torchvision
- Models: CRAFT detection, CRNN recognition (ResNet/VGG, LSTM, CTC)
Also in Data and scraping for AI
See all 13| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 78 out of 100 |
| 2 | Crawl4AIPython web crawler that converts pages to LLM-ready Markdown and JSON | 77 out of 100 |
| 3 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 76 out of 100 |
| #4 | markitdownPython tool that converts PDF, Office, HTML and audio files to Markdown for LLMs | 71 out of 100 |
| #5 | FirecrawlWeb scraping and crawling API that returns LLM-ready markdown | 67 out of 100 |