Downloads · 30 days
0
PP-OCRv4_server_rec_doc_onnx
tobiichioriguchi/PP-OCRv4_server_rec_doc_onnx
PP-OCRv4_server_rec_doc_onnx is a image-to-text model from tobiichioriguchi. Use it when you need a caption or text from an image. It is set up for onnxruntime. The card lists the license as apache-2.0.
ONNX conversion of PaddlePaddle's official PP-OCRv4serverrecdoc text recognition inference model.
Access
Public
Updated Aug 3, 2026
Repo size
94.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx94.9 MB · 100%
At a glance
- Task
- Image-to-Text
- Library
- onnxruntime
- License
- apache-2.0
- Access
- Public
- Created
- Aug 3, 2026
- Updated
- Aug 3, 2026
- SHA
- 7efbc875
Model card
From the Hugging Face model README
PP-OCRv4_server_rec_doc ONNX
ONNX conversion of PaddlePaddle's official PP-OCRv4_server_rec_doc text recognition inference model.
Provenance
- Upstream archive: https://paddle-model-ecology.bj.bcebos.com/paddlex/official_inference_model/paddle3.0.0/PP-OCRv4_server_rec_doc_infer.tar
- Upstream projects: PaddleOCR and PaddleX
- Conversion environment: PaddlePaddle 3.3.0, PaddleX 3.7.0, paddle2onnx 2.0.2rc3
- ONNX opset: 11
Validation
The graph passed onnx.checker, loaded and ran with ONNX Runtime 1.28.0 on CPU, and was compared numerically with the original Paddle inference graph using the same deterministic float32 input. Maximum absolute output error: 7.092952728271484e-6.
Runtime files
inference.onnx: converted model graph and weightsinference.yml: upstream preprocessing, postprocessing, and label metadata
This repository contains a format conversion, not a retrained model. Consult the upstream PaddleOCR documentation for model scope, accuracy, and intended use.
- Task
- Image-to-Text
- Library
- onnxruntime
- License
- apache-2.0
- Created
- Aug 3, 2026
- Updated
- Aug 3, 2026