PDFCopy OCR assets

Text detection: PaddleOCR PP-OCRv6_medium_det (local ONNX export/quantized artifact).
Text recognition: PaddleOCR PP-OCRv6_small_rec (local ONNX export).
Copyright PaddlePaddle Authors. Licensed under the Apache License, Version 2.0.
See LICENSE.txt for the model license.
Project: https://github.com/PaddlePaddle/PaddleOCR
Official model information:
https://huggingface.co/PaddlePaddle/PP-OCRv6_medium_det_onnx
https://huggingface.co/PaddlePaddle/PP-OCRv6_small_rec_onnx

These model files were supplied locally for this project. Their hashes differ
from the current official ONNX downloads. Runtime configuration is taken from
the supplied inference.yml files. See paddle-v6/config.json for file hashes.
The generated runtime configuration and JavaScript preprocessing are adaptations
for browser execution. The ONNX weights are copied without further modification.

ONNX Runtime Web 1.23.2
Copyright Microsoft Corporation. MIT License.
https://github.com/microsoft/onnxruntime
See ONNX-RUNTIME-LICENSE.txt for its license and ONNX-RUNTIME-NOTICES.txt for notices.

Polygon offsetting uses clipper-lib (Clipper). Its library and license are
included under the Boost Software License 1.0. See CLIPPER-LICENSE.txt.
https://www.boost.org/LICENSE_1_0.txt