JaidedAI /EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
★ 30,141⑂ 3,623👁 327⑃ 289● 1,087▤ 23
+0
Daily
+20
Weekly
+65
Monthly
30,141
stars
3,623
forks
327
watchers
289
prs
1,087
issues
23
releases
README
EasyOCR
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including: Latin, Chinese, Arabic, Devanagari, Cyrillic, etc.
Try Demo on our website
Integrated into Huggingface Spaces 🤗 using Gradio. Try out the Web Demo:
What's new
- 24 September 2024 - Version 1.7.2
- Fix several compatibilities
- Read all release notes
What's coming next
- Handwritten text support
Examples
!example
!example2
!example3
Installation
Install using pip
For the latest stable release:
bash
pip install easyocr
For the latest development release:
bash
pip install git+https://github.com/JaidedAI/EasyOCR.git
Note 1: For Windows, please install torch and torchvision first by following the official instructions here https://pytorch.org. On the pytorch website, be sure to select the right CUDA version you have. If you intend to run on CPU mode only, select CUDA = None.
Note 2: We also provide a Dockerfile here.
Note 3: The optional DBNet detector (detect_network='dbnet18') compiles its C++/CUDA ops on first use, which needs the Ninja build tool. To install it along with EasyOCR, use pip install "easyocr[dbnet]".
Usage
python
import easyocr
reader = easyocr.Reader(['ch_sim','en']) this needs to run only once to load the model into memory
result = reader.readtext('chinese.jpg')
The output will be in a list format, each item represents a bounding box, the text detected and confident level, respectively.
bash
[([[189, 75], [469, 75], [469, 165], [189, 165]], '愚园路', 0.3754989504814148),
([[86, 80], [134, 80], [134, 128], [86, 128]], '西', 0.40452659130096436),
([[517, 81], [565, 81], [565, 123], [517, 123]], '东', 0.9989598989486694),
([[78, 126], [136, 126], [136, 156], [78, 156]], '315', 0.8125889301300049),
([[514, 126], [574, 126], [574, 156], [514, 156]], '309', 0.4971577227115631),
([[226, 170], [414, 170], [414, 220], [226, 220]], 'Yuyuan Rd.', 0.8261902332305908),
([[79, 173], [125, 173], [125, 213], [79, 213]], 'W', 0.9848111271858215),
([[529, 173], [569, 173], [569, 213], [529, 213]], 'E', 0.8405593633651733)]
Note 1: ['ch_sim','en'] is the list of languages you want to read. You can pass
several languages at once but not all languages can be used together.
English is compatible with every language and languages that share common characters are usually compatible with each other.
Note 2: Instead of the filepath chinese.jpg, you can also pass an OpenCV image object (numpy array) or an image file as bytes. A URL to a raw image is also acceptable.
Note 3: The line reader = easyocr.Reader(['ch_sim','en']) is for loading a model into memory. It takes some time but it needs to be run only once.
You can also set detail=0 for simpler output.
python
reader.readtext('chinese.jpg', detail = 0)
Result:
bash
['愚园路', '西', '东', '315', '309', 'Yuyuan Rd.', 'W', 'E']
Model weights for the chosen language will be automatically downloaded or you can
download them manually from the model hub and put thTop issues
#746Export to ONNX and use ONNX Runtime, working. Guide.43 comments · 2022-06-05#1077AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS'27 comments · 2023-07-09#704easyocr terminates without any error but don't output anything24 comments · 2022-04-10#892How to replace the best_accuracy.pth with arabic.pth ?23 comments · 2022-11-25#786Repository with all models in ONNX format20 comments · 2022-07-17#815Easyocr memory leak19 comments · 2022-08-08#709[offtopic] make a reimplementation in C++17 comments · 2022-04-12#1034EasyOCR (1.7.0: `-215:Assertion failed) !ssize.empty()` cv2 Error15 comments · 2023-05-26
Discussions
#1470License question regarding pretrained models for internal business use1 comments · 2026-11-12#1467License and redistribution clarification for EasyOCR Japanese model files0 comments · 2026-10-21#1461Open benchmark for burned-in video subtitle OCR — watermark-adjacent text tanks CER 2-2.6x across every engine we tested1 comments · 2026-08-18#1458Who is jaided ai?0 comments · 2026-06-14#1451Has anyone run this inside AWS Fargate?0 comments · 2026-01-20#1449Warning issued when running on CPU0 comments · 2026-01-07#1442How to fasten the text extraction of a video1 comments · 2025-10-30#1441Add Deepseek OCR0 comments · 2025-10-26
Latest release
v1.7.2 v1.7.2 2024-09-24- 24 September 2024 - Version 1.7.2
- Fix several compatibilities