ONNX for Speech To Text

I've been trying to implement a speech to text app using .Net and C#, but it seems that there is no way to simply download a model (e.g. Whisper or Wav2Vec2) and directly call it the way you can in Python. Instead I'm told I need to write all the pre-processing, adding complex code into the application. I've been trying avoid using Python (for good reasons), but it feels like the ONNX route is just too complicated. Am I missing something, like a good library that can do the pre-processing, or a model that has good built in support for .Net?