def __init__(self, hparams):
super(Postnet, self).__init__()
self.convolutions = nn.ModuleList()
self.convolutions.append(
nn.Sequential(
ConvNorm(hparams.n_mel_channels,
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_mel_channels,
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_mel_channels)))
def __init__(self, attention_n_filters, attention_kernel_size,
attention_dim):
super(LocationLayer, self).__init__()
padding = int((attention_kernel_size - 1) / 2)
self.location_conv = ConvNorm(2,
attention_n_filters,
kernel_size=attention_kernel_size,
padding=padding,
bias=False,
stride=1,
dilation=1)
self.location_dense = LinearNorm(attention_n_filters,
attention_dim,
bias=False,
w_init_gain='tanh')
def __init__(self, hparams):
super(Encoder, self).__init__()
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)