docato/PaddleOCR_Mobile_Models
By docato · ↓ 0 · ♥ 0 · Updated 2025-06-18
What's in this repo
This page lists the files in docato/PaddleOCR_Mobile_Models, including Multilingual_PP-OCRv3_det_infer.onnx, PP-OCRv3_mobile_det_infer.onnx, ch_ppocr_mobile_v2.0_cls_infer.onnx and more.
- 8 ONNX models (.onnx files)
- 10 files, including 8 .onnx, 1 .md
- Last updated 2025-06-18
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/Multilingual_PP-OCRv3_det_infer.onnx | — | Download |
| onnx/PP-OCRv3_mobile_det_infer.onnx | — | Download |
| onnx/ch_ppocr_mobile_v2.0_cls_infer.onnx | — | Download |
| onnx/latin_PP-OCRv3_mobile_rec_infer.onnx | — | Download |
| onnx_optimized/Multilingual_PP-OCRv3_det_infer.onnx | — | Download |
| onnx_optimized/PP-OCRv3_mobile_det_infer.onnx | — | Download |
| onnx_optimized/ch_ppocr_mobile_v2.0_cls_infer.onnx | — | Download |
| onnx_optimized/latin_PP-OCRv3_mobile_rec_infer.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
PaddleOCR Mobile Quantized Models (ONNX)
Overview
This repo hosts four ONNX models converted from PaddleOCR mobile checkpoints
| File | Task | Language scope | Input shape |
|---|---|---|---|
Multilingual_PP-OCRv3_det_infer.onnx |
Text-detection | 80+ scripts | NCHW • 1×3×H×W |
PP-OCRv3_mobile_det_infer.onnx |
Text-detection | Latin only | 1×3×H×W |
ch_ppocr_mobile_v2.0_cls_infer.onnx |
Angle classifier | Chinese/Latin | 1×3×H×W |
latin_PP-OCRv3_mobile_rec_infer.onnx |
Text-recognition | Latin | 1×3×H×W |
All models were:
- exported with paddle2onnx 1.2.3 (
opset 11) - simplified via onnx-simplifier 0.4+
Quick Start
import onnxruntime as ort, numpy as np
img = np.random.rand(1, 3, 224, 224).astype("float32")
det = ort.InferenceSession("Multilingual_PP-OCRv3_det_infer.onnx")
cls = ort.InferenceSession("ch_ppocr_mobile_v2.0_cls_infer.onnx")
rec = ort.InferenceSession("latin_PP-OCRv3_mobile_rec_infer.onnx")
det_out = det.run(None, {det.get_inputs()[0].name: img})[0]
# add your post-processing / cropping / decoding here …
Model info
Created: 2025-06-18
Updated: 2025-06-18
View on Hugging FaceFiles (10)
Related models
More from docato
No other models by this author.
More models
No task type declared.