Simple audio training - STFT

simple_audio_pi_gist1.py

def stft(x):
    f, t, spec = signal.stft(x.numpy(), fs=16000, nperseg=255, noverlap = 124, nfft=256)
    return tf.convert_to_tensor(np.abs(spec))

def get_spectrogram(waveform):
  # Padding for files with less than 16000 samples
  zero_padding = tf.zeros([16000] - tf.shape(waveform), dtype=tf.float32)

  # Concatenate audio with padding so that all audio clips will be of the 
  # same length
  waveform = tf.cast(waveform, tf.float32)
  equal_length = tf.concat([waveform, zero_padding], 0)
    
  spectrogram = tf.py_function(func=stft, inp=[equal_length], Tout=tf.float32)
       
  spectrogram.set_shape((129, 124))
  
  return spectrogram