soprano/vocos/modules.py

import torch
from torch import nn


class ConvNeXtBlock(nn.Module):
    """ConvNeXt Block adapted from https://github.com/facebookresearch/ConvNeXt to 1D audio signal.

    Args:
        dim (int): Number of input channels.
        intermediate_dim (int): Dimensionality of the intermediate layer.
        layer_scale_init_value (float, optional): Initial value for the layer scale. None means no scaling.
            Defaults to None.
    """

    def __init__(
        self,
        dim: int,
        intermediate_dim: int,
        layer_scale_init_value: float,
        dw_kernel_size: int = 9,
    ):
        super().__init__()
        self.dwconv = nn.Conv1d(dim, dim, kernel_size=dw_kernel_size, padding=dw_kernel_size//2, groups=dim)  # depthwise conv
        self.norm = nn.LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, intermediate_dim)  # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(intermediate_dim, dim)
        self.gamma = (
            nn.Parameter(layer_scale_init_value * torch.ones(dim), requires_grad=True)
            if layer_scale_init_value > 0
            else None
        )

    def forward(self, x: torch.Tensor) -> torch.Tensor:
        residual = x
        x = self.dwconv(x)
        x = x.transpose(1, 2)  # (B, C, T) -> (B, T, C)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.transpose(1, 2)  # (B, T, C) -> (B, C, T)

        x = residual + x
        return x