def combine_silent(self, effective: numpy.ndarray, feature: AcousticFeature):
sizes = AcousticFeature.get_sizes(
sampling_rate=self._param.sampling_rate,
order=self._param.order,
)
silent_feature = AcousticFeature.silent(len(effective), sizes=sizes, keys=('mc', 'ap', 'f0', 'voiced'))
silent_feature.indexing_set(effective, feature)
return silent_feature
def post_convert(self, start_time: float, time_length: float):
sizes = AcousticFeature.get_sizes(sampling_rate=self.sampling_rate, order=self.order)
keys = ['f0', 'ap', 'sp', 'voiced']
out_feature = self.fetch(
start_time=start_time,
time_length=time_length,
data_stream=self._out_feature_stream,
rate=1000 / self.frame_period,
pad_function=lambda length: AcousticFeature.silent(length, sizes=sizes, keys=keys),
pick_function=lambda segment, first, last: segment.feature.pick(first, last, keys=keys),
concat_function=lambda buffers: AcousticFeature.concatenate(buffers, keys=keys),
)
out_wave = self.vocoder.decode(
acoustic_feature=out_feature,
)
w = out_wave.wave
w[numpy.isnan(w)] = 0
out_wave = Wave(wave=w, sampling_rate=out_wave.sampling_rate)
return out_wave
def pad(self, width: int):
sizes = AcousticFeature.get_sizes(
sampling_rate=self.wave_sampling_rate, order=self.order)
return AcousticFeature.silent(width, sizes=sizes, keys=self._keys)