So, I’m using the C++ library of the trained model and the Pico SDK to write my own firmware to run continuous classification. Is there a way I can use the KY-038 microphone module or there is a specific type of module that can be used?
I am not familiar with that microphone but I don’t see any reason why it should not work.
Just make sure to sample the data at the same frequency and with the same parameters both in your training data and the data used during the inference.
See this thread as well were this was discussed. Hope it helps.