def __init__(self, hparams): super(Postnet, self).__init__() self.convolutions = nn.ModuleList() self.convolutions.append( nn.Sequential( ConvNorm(hparams.n_acoustic_feat_dims, hparams.postnet_embedding_dim, kernel_size=hparams.postnet_kernel_size, stride=1, padding=int((hparams.postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='tanh'), nn.BatchNorm1d(hparams.postnet_embedding_dim)) ) for i in range(1, hparams.postnet_n_convolutions - 1): self.convolutions.append( nn.Sequential( ConvNorm(hparams.postnet_embedding_dim, hparams.postnet_embedding_dim, kernel_size=hparams.postnet_kernel_size, stride=1, padding=int((hparams.postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='tanh'), nn.BatchNorm1d(hparams.postnet_embedding_dim)) ) self.convolutions.append( nn.Sequential( ConvNorm(hparams.postnet_embedding_dim, hparams.n_acoustic_feat_dims, kernel_size=hparams.postnet_kernel_size, stride=1, padding=int((hparams.postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='linear'), nn.BatchNorm1d(hparams.n_acoustic_feat_dims)) )
def __init__(self, n_mel_channels, postnet_embedding_dim, postnet_kernel_size, postnet_n_convolutions): super(Postnet, self).__init__() self.convolutions = nn.ModuleList() self.convolutions.append( nn.Sequential( ConvNorm(n_mel_channels, postnet_embedding_dim, kernel_size=postnet_kernel_size, stride=1, padding=int((postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='tanh'), nn.BatchNorm1d(postnet_embedding_dim)) ) for i in range(1, postnet_n_convolutions - 1): self.convolutions.append( nn.Sequential( ConvNorm(postnet_embedding_dim, postnet_embedding_dim, kernel_size=postnet_kernel_size, stride=1, padding=int((postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='tanh'), nn.BatchNorm1d(postnet_embedding_dim)) ) self.convolutions.append( nn.Sequential( ConvNorm(postnet_embedding_dim, n_mel_channels, kernel_size=postnet_kernel_size, stride=1, padding=int((postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='linear'), nn.BatchNorm1d(n_mel_channels)) ) self.n_convs = len(self.convolutions)
def __init__(self, hparams): super(Encoder, self).__init__() self.prenet = Prenet( hparams.n_symbols, [hparams.symbols_embedding_dim, hparams.symbols_embedding_dim]) convolutions = [] for _ in range(hparams.encoder_n_convolutions): conv_layer = nn.Sequential( ConvNorm(hparams.encoder_embedding_dim, hparams.encoder_embedding_dim, kernel_size=hparams.encoder_kernel_size, stride=1, padding=int((hparams.encoder_kernel_size - 1) / 2), dilation=1, w_init_gain='relu'), nn.BatchNorm1d(hparams.encoder_embedding_dim)) convolutions.append(conv_layer) self.convolutions = nn.ModuleList(convolutions) self.lstm = nn.LSTM(hparams.encoder_embedding_dim, int(hparams.encoder_embedding_dim / 2), 1, batch_first=True, bidirectional=True)
def __init__( self, encoder_n_convolutions, # Number of encoder convolutions; def. 3 encoder_embedding_dim, # Encoder embedding dimension; def. 512 encoder_kernel_size # Encoder kernel size; def. 5 ): super(Encoder, self).__init__() convolutions = [] for _ in range(encoder_n_convolutions): conv_layer = nn.Sequential( ConvNorm(encoder_embedding_dim, encoder_embedding_dim, kernel_size=encoder_kernel_size, stride=1, padding=int((encoder_kernel_size - 1) / 2), dilation=1, w_init_gain='relu'), nn.BatchNorm1d(encoder_embedding_dim)) convolutions.append(conv_layer) self.convolutions = nn.ModuleList(convolutions) self.lstm = nn.LSTM(encoder_embedding_dim, int(encoder_embedding_dim / 2), 1, batch_first=True, bidirectional=True)
def __init__(self, attention_n_filters, attention_kernel_size, attention_dim): super(LocationLayer, self).__init__() self.location_conv = ConvNorm(1, attention_n_filters, kernel_size=attention_kernel_size, padding=int((attention_kernel_size - 1) / 2), stride=1, dilation=1) self.location_dense = LinearNorm(attention_n_filters, attention_dim, bias=False, w_init_gain='tanh')
def __init__( self, n_mel_channels: int, # Number of bins in mel-spectrograms; def. 80 postnet_embedding_dim: int, # Postnet embedding dimension; def. 512 postnet_kernel_size: int, # Postnet kernel size; def. 5 postnet_n_convolutions: int # Number of postnet convolutions; def. 5 ): super(Postnet, self).__init__() self.convolutions = nn.ModuleList() self.convolutions.append( nn.Sequential( ConvNorm(n_mel_channels, postnet_embedding_dim, kernel_size=postnet_kernel_size, stride=1, padding=int((postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='tanh'), nn.BatchNorm1d(postnet_embedding_dim))) for i in range(1, postnet_n_convolutions - 1): self.convolutions.append( nn.Sequential( ConvNorm(postnet_embedding_dim, postnet_embedding_dim, kernel_size=postnet_kernel_size, stride=1, padding=int((postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='tanh'), nn.BatchNorm1d(postnet_embedding_dim))) self.convolutions.append( nn.Sequential( ConvNorm(postnet_embedding_dim, n_mel_channels, kernel_size=postnet_kernel_size, stride=1, padding=int((postnet_kernel_size - 1) / 2), dilation=1, w_init_gain='linear'), nn.BatchNorm1d(n_mel_channels))) self.n_convs = len(self.convolutions)