def input_types(self):
return {
"z": NeuralType(('B', 'flowgroup', 'T'), NormalDistributionSamplesType()),
"logdet": NeuralType(elements_type=VoidType()),
"gt_audio": NeuralType(('B', 'T'), AudioSignal()),
"predicted_audio": NeuralType(('B', 'T'), AudioSignal()),
"sigma": NeuralType(optional=True),
}
def output_types(self):
return {
"z": NeuralType(('B', 'D', 'T'), NormalDistributionSamplesType()),
"y_m": NeuralType(('B', 'D', 'T'), NormalDistributionMeanType()),
"y_logs": NeuralType(('B', 'D', 'T'), NormalDistributionLogVarianceType()),
"logdet": NeuralType(('B'), LogDeterminantType()),
"log_durs_predicted": NeuralType(('B', 'T'), TokenLogDurationType()),
"log_durs_extracted": NeuralType(('B', 'T'), TokenLogDurationType()),
"spect_lengths": NeuralType(('B'), LengthsType()),
"attn": NeuralType(('B', 'T', 'T'), SequenceToSequenceAlignmentType()),
}
def output_types(self):
if self.mode == OperationMode.training or self.mode == OperationMode.validation:
return {
"pred_normal_dist": NeuralType(('B', 'flowgroup', 'T'), NormalDistributionSamplesType()),
"logdet": NeuralType(elements_type=VoidType()),
"audio_pred": NeuralType(('B', 'T'), AudioSignal()),
}
else:
return {
"audio": NeuralType(('B', 'T'), AudioSignal()),
}
def input_types(self):
return {
"z":
NeuralType(('B', 'flowgroup', 'T'),
NormalDistributionSamplesType()),
"log_s_list":
[NeuralType(('B', 'flowgroup', 'T'),
VoidType())], # TODO: Figure out a good typing
"log_det_W_list": [NeuralType(elements_type=VoidType())
], # TODO: Figure out a good typing
"sigma":
NeuralType(optional=True),
}
def output_types(self):
if self.mode == OperationMode.training or self.mode == OperationMode.validation:
output_dict = {
"pred_normal_dist": NeuralType(('B', 'flowgroup', 'T'), NormalDistributionSamplesType()),
"logdet": NeuralType(elements_type=LogDeterminantType()),
"predicted_audio": NeuralType(('B', 'T'), AudioSignal()),
}
if self.mode == OperationMode.validation:
output_dict["spec"] = NeuralType(('B', 'T', 'D'), MelSpectrogramType())
output_dict["spec_len"] = NeuralType(('B'), LengthsType())
return output_dict
return {
"audio_pred": NeuralType(('B', 'T'), AudioSignal()),
}
def output_types(self):
if self.mode == OperationMode.training or self.mode == OperationMode.validation:
output_dict = {
"pred_normal_dist": NeuralType(('B', 'flowgroup', 'T'), NormalDistributionSamplesType()),
"log_s_list": NeuralType(('B', 'flowgroup', 'T'), VoidType()), # TODO: Figure out a good typing
"log_det_W_list": NeuralType(elements_type=VoidType()), # TODO: Figure out a good typing
}
if self.mode == OperationMode.validation:
output_dict["audio_pred"] = NeuralType(('B', 'T'), AudioSignal())
output_dict["spec"] = NeuralType(('B', 'T', 'D'), MelSpectrogramType())
output_dict["spec_len"] = NeuralType(('B'), LengthsType())
return output_dict
return {
"audio_pred": NeuralType(('B', 'T'), AudioSignal()),
}
def output_types(self):
return {
"z": NeuralType(('B', 'D', 'T'), NormalDistributionSamplesType()),
"logdet_tot": NeuralType(('B',), LogDeterminantType()),
}
