Support for different PCM sample rates (8kHz) in CreateSpeechRecognizerWithStream
If you create a recognizer with CreateSpeechRecognizerWithStream, you need to provide an AudioInputStreamFormat. This class only supports 16000 for SamplesPerSec. I'd like to have support for 8000 to be able to hook directly to a VoIP call. I was able to get it working with nAudio, but it needs an inline transcode, which can be expensive.