def save_audio(mag_spec, logdir, name, stft, train=True): magnitudes = dynamic_range_decompression(mag_spec) magnitudes = torch.pow(magnitudes, 1.2) magnitudes = torch.unsqueeze(magnitudes, 0) # magnitudes = torch.t(magnitudes) # print(magnitudes.shape) signal = griffin_lim(magnitudes.cpu(), stft.stft_fn) signal = signal.data.cpu().numpy() if train: file_name = '{}/sample_train_step_{}.wav'.format(logdir, name) else: file_name = '{}/sample_eval_step_{}.wav'.format(logdir, name) if logdir[0] != '/': file_name = "./"+file_name print(signal.shape) # signal = signal.astype(np.int16) signal = signal[0] # print(signal) write(file_name, 22050 ,signal)
def spectral_de_normalize(self, magnitudes): output = dynamic_range_decompression(magnitudes) return output
def normalize_mel(mel, mean, sigma): normalized = dynamic_range_decompression(mel) normalized = convert_mel(normalized) normalized = (np.log10(normalized) - mean) / sigma return normalized