def _process_utterance(mel_dir, linear_dir, wav_dir, index, wav_path, text,
speaker_num, lan_num, hparams):
"""
Preprocesses a single utterance wav/text pair
this writes the mel scale spectogram to disk and return a tuple to write
to the train.txt file
Args:
- mel_dir: the directory to write the mel spectograms into
- linear_dir: the directory to write the linear spectrograms into
- wav_dir: the directory to write the preprocessed wav into
- index: the numeric index to use in the spectogram filename
- wav_path: path to the audio file containing the speech input
- text: text spoken in the input audio file
- hparams: hyper parameters
Returns:
- A tuple: (audio_filename, mel_filename, linear_filename, time_steps, mel_frames, linear_frames, text)
"""
try:
# Load the audio as numpy array
wav = audio.load_wav(wav_path, sr=hparams.sample_rate)
except FileNotFoundError: #catch missing wav exception
print(
'file {} present in csv metadata is not present in wav folder. skipping!'
.format(wav_path))
return None
#rescale wav
if hparams.rescale:
wav = wav / np.abs(wav).max() * hparams.rescaling_max
#M-AILABS extra silence specific
if hparams.trim_silence:
wav = audio.trim_silence(wav, hparams)
#Get spectrogram from wav
ret = audio.wav2spectrograms(wav, hparams)
if ret is None:
return None
out, mel_spectrogram, linear_spectrogram, time_steps, mel_frames = ret
# Write the spectrogram and audio to disk
audio_filename = 'audio-{}.npy'.format(index)
mel_filename = 'mel-{}.npy'.format(index)
linear_filename = 'linear-{}.npy'.format(index)
np.save(os.path.join(wav_dir, audio_filename),
out.astype(np.float32),
allow_pickle=False)
np.save(os.path.join(mel_dir, mel_filename),
mel_spectrogram.T,
allow_pickle=False)
np.save(os.path.join(linear_dir, linear_filename),
linear_spectrogram.T,
allow_pickle=False)
# Return a tuple describing this training example
return (audio_filename, mel_filename, linear_filename, time_steps,
mel_frames, text, speaker_num, lan_num)
def audio_process_utterance(mel_dir, linear_dir, wav_dir, duration_dir,
score_dir, index, wav, durations, scores, hparams):
"""
Preprocesses a single utterance wav/text pair
this writes the mel scale spectogram to disk and return a tuple to write
to the train.txt file
Args:
- mel_dir: the directory to write the mel spectograms into
- linear_dir: the directory to write the linear spectrograms into
- wav_dir: the directory to write the preprocessed wav into
- index: the numeric index to use in the spectogram filename
- wav_path: path to the audio file containing the speech input
- hparams: hyper parameters
Returns:
- A tuple: (audio_filename, mel_filename, linear_filename, score_filename, duration_filename, time_steps, mel_frames)
"""
#rescale wav
if hparams.rescale:
wav = wav / np.abs(wav).max() * hparams.rescaling_max
#Get spectrogram from wav
ret = audio.wav2spectrograms(wav, hparams)
if ret is None:
return None
out = ret[0]
mel_spectrogram = ret[1]
linear_spectrogram = ret[2]
time_steps = ret[3]
mel_frames = ret[4]
# Write the spectrogram and audio to disk
audio_filename = 'audio-{}.npy'.format(index)
mel_filename = 'mel-{}.npy'.format(index)
linear_filename = 'linear-{}.npy'.format(index)
duration_filename = 'duration-{}.npy'.format(index)
score_filename = 'score-{}.npy'.format(index)
np.save(os.path.join(wav_dir, audio_filename),
out.astype(np.float32),
allow_pickle=False)
np.save(os.path.join(mel_dir, mel_filename),
mel_spectrogram.T,
allow_pickle=False)
np.save(os.path.join(linear_dir, linear_filename),
linear_spectrogram.T,
allow_pickle=False)
np.save(os.path.join(duration_dir, duration_filename),
durations,
allow_pickle=False)
np.save(os.path.join(score_dir, score_filename),
scores,
allow_pickle=False)
# Return a tuple describing this training example
return (audio_filename, mel_filename, linear_filename, duration_filename,
score_filename, time_steps, mel_frames)
