Onnxruntime-extensions

**New Changes:**

1. NuGet package for the .NET platform. This package offers comprehensive platform support, including Windows, Linux, MacOS, Android, and iOS. Both x64 and arm64 architectures are supported, where applicable.
2. Support for pre-processing and post-processing of the Whisper model, inclusive of Audio and Tokenizer decoding operators.
3. Extends support for pre-processing and post-processing of object-detection models, including a new DrawBoundingBoxes operator. Pre/post processing tools can add non-max-suppression to the model to select the best bounding boxes, and scale those to the original image. See the end-to-end example in `tutorials/yolo_e2e.py`.
4. Introduces the Audio Domain, complemented with AudioCodec and optimized STFT Operators, enhancing audio processing capabilities.
5. Enabled optional input/output support for some operators such as GPT2Tokenizer, ClipTokenizer, and RobertaTokenizer.
6. Refined the implementation of offset mapping for BBPE-style tokenizers for more operators and efficiency improvement.
7. Other bug and security fixes.

Contributions
Contributors to ONNX Runtime Extensions include members across teams at Microsoft, along with our community members: edgchen1 kunal-vaishnavi sayanshaw24 skottmckay snnn VishalX wenbingl wejoncy

**Full Changelog**: https://github.com/microsoft/onnxruntime-extensions/compare/v0.7.0...v0.8.0

**General**
1. New custom operators: RobertaTokenizer, ClipTokenizer, EncodeImage, DecodeImage
2. ORT custom operator C++ stub generation [tool](https://github.com/microsoft/onnxruntime-extensions/blob/main/tools/gen_customop_template.py)
3. Operator implementation and [documentation](https://github.com/microsoft/onnxruntime-extensions/tree/rel-0.7/docs) improved.
4. Python (3.7 - 3.10) and ORT (1.10 above) compatible.

**Mobile**
1. Android package: [Maven](https://mvnrepository.com/artifact/com.microsoft.onnxruntime/onnxruntime-extensions-android)
2. iOS package: [CocoaPods](https://github.com/CocoaPods/Specs/tree/master/Specs/7/f/9/onnxruntime-extensions-c/0.7.0)
3. [PrePostProcessor](https://github.com/microsoft/onnxruntime-extensions/blob/main/onnxruntime_extensions/tools/Example%20usage%20of%20the%20PrePostProcessor.md) tool for mobile model
4. [Super-resolution model pre- / post- processing end-to-end examples](https://github.com/microsoft/onnxruntime-extensions/blob/rel-0.7/tutorials/superresolution_e2e.py)

Contributors to this release include members across teams at Microsoft, along with our community members: edgchen1 skottmckay shaahji sayanshaw24 snnn wenbingl natke YUNQIUGUO guschmue JamieMagee adrianlizarraga wejoncy matheusgomes28

This is a C++ source code package only release. Python and other packages will be expected in the next release.

What's Changed
1. Support OpenCV core and imgproc modules in Custom Op implementation.
2. Code security compliance fixings.
3. Some other improvements.

Thanks for the Contributors from: joburkho shaahji TruscaPetre Sanster natke hombreola snnn leqiao-1 wenbingl

Fix the issue on StringRegexSplitWithOffsets operator.

Correct memory indexing issue.

This release improved the process and the features required for ONNXRuntime Mobile and ONNXRuntime Web,
Specifically
1. Support Android/Web-Assembly build
2. Support the custom build for the selected operators
3. Support non-exception C++ build
4. Add mobile-optimized operators for string manipulation and tokenization
5. The GPT-2 beam search tool
6. Some bug fixings