microWakeWord-Trainer-Nvidi…/WHATS_NEW.md

- Added Parakeet ONNX as a second local Auto Training STT engine alongside Faster Whisper.
- Replaced manual model, device, and compute fields with a simple engine selector and managed language-aware models.
- Added CUDA-enabled ONNX Runtime with CPU fallback, runtime reporting, and model-cache cleanup when switching engines.
	`- Added Parakeet ONNX as a second local Auto Training STT engine alongside Faster Whisper.`
	`- Replaced manual model, device, and compute fields with a simple engine selector and managed language-aware models.`
	`- Added CUDA-enabled ONNX Runtime with CPU fallback, runtime reporting, and model-cache cleanup when switching engines.`