jingsongliujing/OnnxOCR
Description and use
Jingsongliujing/OnnxOCR is a lightweight optical character recognition (OCR) solution that re‑implements PaddleOCR using the ONNX runtime, removing the dependency on the PaddlePaddle training framework. By converting the original models to ONNX, it delivers ultra‑fast inference while retaining high accuracy, making it well suited for real‑time or resource‑constrained applications.
Use in a workflow
jingsongliujing/OnnxOCR may be useful when its README and activity match a concrete workflow.
Limitations and review notes
Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.
- Source: github
- Language: Python
- Record date: 2026-09-05T17:31:24.133Z