You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We need to have several plots for the data that we will need to process. This should include:
Raw Audio data: To see what kind of audio are we parsing into the FFT. (This should include all the )
Spectrogram: To see the frequency components of the audio in respect to time.
Whistle Detector Output: Once the FFT outputs is parsed into the whistle NN, it should output the float value into a plot.
Optional (but nice to have graphs):
Mono Audio stream: Since the current RoboÉireann codebase down-mixes the audio buffers from the microphones down to a mono stream and scales the data by a set gain, this output is nice to see the final audio data before being parsed into the FFT.
The text was updated successfully, but these errors were encountered:
We need to have several plots for the data that we will need to process. This should include:
Optional (but nice to have graphs):
The text was updated successfully, but these errors were encountered: