RapidOCR model mirror (watts-ai)

A verbatim mirror of a small subset of the RapidAI/RapidOCR model files, re-hosted on Hugging Face so that downstream services can fetch the weights from Hugging Face instead of modelscope.cn.

The files here are byte-for-byte copies of the corresponding files in the upstream ModelScope repository at tag v3.8.0. No files were modified. The relative paths are preserved, so a URL such as

https://www.modelscope.cn/models/RapidAI/RapidOCR/resolve/v3.8.0/torch/PP-OCRv4/rec/latin_PP-OCRv3_rec_mobile.pth

maps to

https://huggingface.co/watts-ai/RapidOCR/resolve/main/v3.8.0/torch/PP-OCRv4/rec/latin_PP-OCRv3_rec_mobile.pth

Contents

Only the files needed by the Latin-script torch OCR pipeline are mirrored:

Path SHA256 Purpose
v3.8.0/torch/PP-OCRv4/det/en_PP-OCRv3_det_mobile.pth 62aba369…d5c139ec92b34c8ac7b9ba7c2846 English text detection
v3.8.0/torch/PP-OCRv4/rec/latin_PP-OCRv3_rec_mobile.pth caf8e0f2…2b69f30258c15bf90 Latin-script text recognition
v3.8.0/torch/PP-OCRv4/cls/ch_ptocr_mobile_v2.0_cls_mobile.pth bfe13860…13f60c98e1 Text-line orientation classifier
v3.8.0/paddle/PP-OCRv4/rec/latin_PP-OCRv3_rec_mobile/latin_dict.txt 8e6d4e36…34429e2c Latin recognition character dictionary

The SHA256 values match those pinned in RapidOCR's default_models.yaml.

License & attribution

Licensed under the Apache License, Version 2.0 — same as the upstream sources. See LICENSE.

This mirror redistributes the above works unmodified, retaining their Apache-2.0 license and attribution as required by Section 4 of the license.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support