Skip to main content

English | 简体中文 |

If you find it useful, please give it a Star.

ONNXOCR

Universal OCR, supporting inference in over 80 languages.

Version Update The PPOCRv4 model converted to an ONNX model for inference achieves higher accuracy and performance, with the inference speed being 5 times faster than using the PaddlePaddle framework.

Advantages:

  1. Independent from deep learning training frameworks, it is a general OCR that can be directly deployed.
  2. In situations where computational power is limited and accuracy remains unchanged, the PaddleOCR is converted into an ONNX model, which has been reconstructed as an OCR model that can be deployed on computers with ARM architecture and x86 architecture.
  3. On computers with equivalent performance, the inference speed has been accelerated by 4-5 times.

Effect Display

Alt text

Alt text

Alt text

Alt text

Alt text

我的微信
QQ群

写在最后

我喜欢开源,喜欢AI技术,因为我认为开源和AI会为有需要的人带来方便和帮助,也会让这个世界变得更好。通过对这些项目的捐赠,您可以和我一道让AI为更多人带来温暖和美好。

I like open source and AI technology because I think open source and AI will bring convenience and help to people in need, and will also make the world a better place. By donating to these projects, you can join me in making AI bring warmth and beauty to more people.

支付宝或微信打赏 (Alipay reward or WeChat reward)¶ 通过支付宝或者微信给作者打赏,请写好备注。 Give the me a reward through Alipay or WeChat.

Star History

Star History Chart

Metadata

Release files for onnxocr 1.0.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for onnxocr 1.0.0
File Size Uploaded
onnxocr-1.0.0.tar.gz 15.0 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for onnxocr 1.0.0
File Interpreter ABI Platform
onnxocr-1.0.0-py3-none-any.whl Python 3 none any Details

Total release size: 29.9 MB

Release files / onnxocr-1.0.0.tar.gz

Download URL onnxocr-1.0.0.tar.gz
Size 15.0 MB
Tags Source
SHA-256 checksum
How to use checksums
cb7aa24d267528e8ed0c5c082a89a13467941e1a2c01c1546be5a996444ec6c0
BLAKE2b-256 checksum
How to use checksums
1fb30620eb3a102eebb451104814ebca4af71377b62dc4382c74800432214018
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.7

Release files / onnxocr-1.0.0-py3-none-any.whl

Download URL onnxocr-1.0.0-py3-none-any.whl
Size 14.9 MB
Tags Python 3
SHA-256 checksum
How to use checksums
db44cd99708e8c9cce9c429cf0508ff418d07a8bbb60e76c5f9b7d958a130219
BLAKE2b-256 checksum
How to use checksums
f2b70671788790917f524f04b55391fdabd573830e7b9d42b1b53973e7de5e0d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.7

Release history Release notifications | RSS feed

4.0.0

2 release files

3.1.1

2 release files

3.1.0

2 release files

2.0.0

2 release files

This release

1.0.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page