Method forward

fireredtts2/codec/decoder.py:492–521

Forward pass of the ISTFTHead module. Args: x (Tensor): Input tensor of shape (B, L, H), where B is the batch size, L is the sequence length, and H denotes the model dimension. Returns: Tensor: Reconstructed time-domain audio

(self, x: torch.Tensor, x_len: torch.Tensor)

        )

    def forward(self, x: torch.Tensor, x_len: torch.Tensor) -> torch.Tensor:
        """
        Forward pass of the ISTFTHead module.

        Args:
            x (Tensor): Input tensor of shape (B, L, H), where B is the batch size,
                        L is the sequence length, and H denotes the model dimension.

        Returns:
            Tensor: Reconstructed time-domain audio signal of shape (B, T), where T is the length of the output signal.
        """
        x_pred = self.out(x)
        x_pred = x_pred.transpose(1, 2)
        mag, p = x_pred.chunk(2, dim=1)
        mag = torch.exp(mag)
        mag = torch.clip(
            mag, max=1e2
        )  # safeguard to prevent excessively large magnitudes
        # wrapping happens here. These two lines produce real and imaginary value
        x = torch.cos(p)
        y = torch.sin(p)
        # recalculating phase here does not produce anything new
        # only costs time
        # phase = torch.atan2(y, x)
        # S = mag * torch.exp(phase * 1j)
        # better directly produce the complex value
        S = mag * (x + 1j * y)
        audio = self.istft(S)
        audio_length = x_len * self.hop_length
        return audio, audio_length

    def forward_chunk(
        self, x: torch.Tensor, cache: torch.Tensor = None, last_chunk: bool = False