Method forward

modules/fastspeech/tts_modules.py:282–307

:param x: [B, T, C] :param padding_mask: [B, T] :return: [B, T, C] or [L, B, T, C]

(self, x, padding_mask=None, attn_mask=None, return_hiddens=False)

            self.layer_norm = None

    def forward(self, x, padding_mask=None, attn_mask=None, return_hiddens=False):
        """
        :param x: [B, T, C]
        :param padding_mask: [B, T]
        :return: [B, T, C] or [L, B, T, C]
        """
        padding_mask = x.abs().sum(-1).eq(0).data if padding_mask is None else padding_mask
        nonpadding_mask_TB = 1 - padding_mask.transpose(0, 1).float()[:, :, None]  # [T, B, 1]
        if self.use_pos_embed:
            positions = self.pos_embed_alpha * self.embed_positions(x[..., 0])
            x = x + positions
            x = F.dropout(x, p=self.dropout, training=self.training)
        # B x T x C -> T x B x C
        x = x.transpose(0, 1) * nonpadding_mask_TB
        hiddens = []
        for layer in self.layers:
            x = layer(x, encoder_padding_mask=padding_mask, attn_mask=attn_mask) * nonpadding_mask_TB
            hiddens.append(x)
        if self.use_last_norm:
            x = self.layer_norm(x) * nonpadding_mask_TB
        if return_hiddens:
            x = torch.stack(hiddens, 0)  # [L, T, B, C]
            x = x.transpose(1, 2)  # [L, B, T, C]
        else:
            x = x.transpose(0, 1)  # [B, T, C]
        return x


class FastspeechEncoder(FFTBlocks):