LibrePPOCRt-ocr

PP-OCRv5 mobile tier (CPU tier) converted to the LibreYOLO checkpoint format: one composite .pt bundling the DB text detector (det.*) and the CTC text recognizer (rec.*) plus the PP-OCRv5 recognition dictionary as charset metadata. Recognition covers Simplified Chinese, Traditional Chinese, English, Japanese, and Chinese pinyin with one dictionary and one model.

from libreyolo import LibreYOLO

model = LibreYOLO("LibrePPOCRt-ocr.pt")
r = model("receipt.jpg")
for poly, text, conf in zip(r.ocr.polygons, r.ocr.texts, r.ocr.conf):
    print(text, float(conf))

Provenance

Converted with weights/convert_ppocr_weights.py from the official Apache-2.0 PP-OCRv5 training checkpoints released by the PaddleOCR project (paper: PaddleOCR 3.0 Technical Report):

Upstream checkpoint	SHA-256
PP-OCRv5_mobile_det_pretrained.pdparams	7e2e3b0bd5bbdcb0b842cb92aaacc2852f80299a4858b8767a45bd0c6e955648
PP-OCRv5_mobile_rec_pretrained.pdparams	04745475b97a1faf029c7442a4c4421b156249b9395814e509bf4a9804e37750

This file: LibrePPOCRt-ocr.pt, SHA-256 b04320735d94e9eb535d9342d4a89b908e0fd4d002cd16991f0e7b0523e77c7c.

The conversion is a name-mapped metadata wrap (batch-norm buffer renames, Linear transposes, det./rec. namespacing); learned parameters are unchanged. Stage parity vs the official PP-OCRv5 inference graphs on identical input tensors: detection maps match to <= 1e-4 and recognition probabilities to <= 6e-5 with identical argmax.

Code and weights are used under the Apache License 2.0. Copyright (c) 2020 PaddlePaddle Authors.