def main():
n_mfcc = 40
model_dir = '../models'
model = Model(model_dir)
signal, rate = au.read_wav('../../audio/trapphus.wav')
signal_segment_list = au.split_signal(signal,
rate=rate,
segment_length=60000,
min_energy=100,
max_energy=4,
debug=False)
signal_segment_list = [
au.pad_to(segment, 2**16) for segment in signal_segment_list
]
mfccs = [
au.waveform_to_mfcc(segment, rate, n_mfcc)[1][:, :-1]
for segment in signal_segment_list
]
nw_input = preprocess(mfccs)
nw_output = model.forward(nw_input)
rir_list = postprocess(nw_output, 0, True)
rir_list_2 = postprocess(nw_output, 20, True)
plt.show()
def preprocess_peaks(signal, fs):
mfcc = au.waveform_to_mfcc(signal, fs, 40)[1][:,:-1]
delta_1, delta_2 = au.calculate_delta_features(mfcc)
mean = np.load('/home/felix/rirnet/database/mean.npy').T
std = np.load('/home/felix/rirnet/database/std.npy').T
normalized = np.nan_to_num((np.array([mfcc, delta_1, delta_2]).T - mean)/std).T
return torch.tensor(normalized).unsqueeze(0).float()
def waveforms_to_mfccs(waveforms, db_setup):
fs = db_setup['fs']
n_mfcc = db_setup['n_mfcc']
mfccs = [
au.waveform_to_mfcc(waveform, fs, n_mfcc)[1][:, :-1]
for waveform in waveforms
]
return mfccs