def __init__(self, attention_rnn_dim, embedding_dim, attention_dim, attention_location_n_filters, attention_location_kernel_size): super(Attention, self).__init__() self.query_layer = LinearNorm(attention_rnn_dim, attention_dim, bias=False, w_init_gain='tanh') self.memory_layer = LinearNorm(embedding_dim, attention_dim, bias=False, w_init_gain='tanh') self.v = LinearNorm(attention_dim, 1, bias=False) self.location_layer = LocationLayer(attention_location_n_filters, attention_location_kernel_size, attention_dim) self.score_mask_value = -float("inf")
def __init__(self, in_dim, sizes): super(Prenet, self).__init__() in_sizes = [in_dim] + sizes[:-1] self.layers = nn.ModuleList([ LinearNorm(in_size, out_size, bias=False) for (in_size, out_size) in zip(in_sizes, sizes) ])
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(Decoder, self).__init__() self.n_mel_channels = hparams.n_mel_channels self.n_frames_per_step = hparams.n_frames_per_step self.encoder_embedding_dim = hparams.encoder_embedding_dim self.attention_rnn_dim = hparams.attention_rnn_dim self.decoder_rnn_dim = hparams.decoder_rnn_dim self.prenet_dim = hparams.prenet_dim self.max_decoder_steps = hparams.max_decoder_steps self.gate_threshold = hparams.gate_threshold self.p_attention_dropout = hparams.p_attention_dropout self.p_decoder_dropout = hparams.p_decoder_dropout self.prenet = Prenet( hparams.n_mel_channels * hparams.n_frames_per_step, [hparams.prenet_dim, hparams.prenet_dim]) self.attention_rnn = nn.LSTMCell( hparams.prenet_dim + hparams.encoder_embedding_dim, hparams.attention_rnn_dim) self.attention_layer = Attention( hparams.attention_rnn_dim, hparams.encoder_embedding_dim, hparams.attention_dim, hparams.attention_location_n_filters, hparams.attention_location_kernel_size) self.decoder_rnn = nn.LSTMCell( hparams.attention_rnn_dim + hparams.encoder_embedding_dim, hparams.decoder_rnn_dim, 1) self.linear_projection = LinearNorm( hparams.decoder_rnn_dim + hparams.encoder_embedding_dim, hparams.n_mel_channels * hparams.n_frames_per_step) self.gate_layer = LinearNorm(hparams.decoder_rnn_dim + hparams.encoder_embedding_dim, 1, bias=True, w_init_gain='sigmoid')