models/vocoders/gan/generator/hifigan.py

# Copyright (c) 2023 Amphion.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.

import torch
import torch.nn.functional as F
import torch.nn as nn
from torch.nn import Conv1d, ConvTranspose1d
from torch.nn.utils import weight_norm, remove_weight_norm
from modules.vocoder_blocks import *


LRELU_SLOPE = 0.1


class ResBlock1(torch.nn.Module):
    def __init__(self, cfg, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(ResBlock1, self).__init__()
        self.cfg = cfg
        self.convs1 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[2],
                        padding=get_padding(kernel_size, dilation[2]),
                    )
                ),
            ]
        )
        self.convs1.apply(init_weights)

        self.convs2 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
            ]
        )
        self.convs2.apply(init_weights)

    def forward(self, x):
        for c1, c2 in zip(self.convs1, self.convs2):
            xt = F.leaky_relu(x, LRELU_SLOPE)
            xt = c1(xt)
            xt = F.leaky_relu(xt, LRELU_SLOPE)
            xt = c2(xt)
            x = xt + x
        return x

    def remove_weight_norm(self):
        for l in self.convs1:
            remove_weight_norm(l)
        for l in self.convs2:
            remove_weight_norm(l)


class ResBlock2(torch.nn.Module):
    def __init__(self, cfg, channels, kernel_size=3, dilation=(1, 3)):
        super(ResBlock2, self).__init__()
        self.cfg = cfg
        self.convs = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
            ]
        )
        self.convs.apply(init_weights)

    def forward(self, x):
        for c in self.convs:
            xt = F.leaky_relu(x, LRELU_SLOPE)
            xt = c(xt)
            x = xt + x
        return x

    def remove_weight_norm(self):
        for l in self.convs:
            remove_weight_norm(l)


class HiFiGAN(torch.nn.Module):
    def __init__(self, cfg):
        super(HiFiGAN, self).__init__()
        self.cfg = cfg
        self.num_kernels = len(self.cfg.model.hifigan.resblock_kernel_sizes)
        self.num_upsamples = len(self.cfg.model.hifigan.upsample_rates)
        self.conv_pre = weight_norm(
            Conv1d(
                cfg.preprocess.n_mel,
                self.cfg.model.hifigan.upsample_initial_channel,
                7,
                1,
                padding=3,
            )
        )
        resblock = ResBlock1 if self.cfg.model.hifigan.resblock == "1" else ResBlock2

        self.ups = nn.ModuleList()
        for i, (u, k) in enumerate(
            zip(
                self.cfg.model.hifigan.upsample_rates,
                self.cfg.model.hifigan.upsample_kernel_sizes,
            )
        ):
            self.ups.append(
                weight_norm(
                    ConvTranspose1d(
                        self.cfg.model.hifigan.upsample_initial_channel // (2**i),
                        self.cfg.model.hifigan.upsample_initial_channel
                        // (2 ** (i + 1)),
                        k,
                        u,
                        padding=(k - u) // 2,
                    )
                )
            )

        self.resblocks = nn.ModuleList()
        for i in range(len(self.ups)):
            ch = self.cfg.model.hifigan.upsample_initial_channel // (2 ** (i + 1))
            for j, (k, d) in enumerate(
                zip(
                    self.cfg.model.hifigan.resblock_kernel_sizes,
                    self.cfg.model.hifigan.resblock_dilation_sizes,
                )
            ):
                self.resblocks.append(resblock(self.cfg, ch, k, d))

        self.conv_post = weight_norm(Conv1d(ch, 1, 7, 1, padding=3))
        self.ups.apply(init_weights)
        self.conv_post.apply(init_weights)

    def forward(self, x):
        x = self.conv_pre(x)
        for i in range(self.num_upsamples):
            x = F.leaky_relu(x, LRELU_SLOPE)
            x = self.ups[i](x)
            xs = None
            for j in range(self.num_kernels):
                if xs is None:
                    xs = self.resblocks[i * self.num_kernels + j](x)
                else:
                    xs += self.resblocks[i * self.num_kernels + j](x)
            x = xs / self.num_kernels
        x = F.leaky_relu(x)
        x = self.conv_post(x)
        x = torch.tanh(x)

        return x

    def remove_weight_norm(self):
        print("Removing weight norm...")
        for l in self.ups:
            remove_weight_norm(l)
        for l in self.resblocks:
            l.remove_weight_norm()
        remove_weight_norm(self.conv_pre)
        remove_weight_norm(self.conv_post)


# todo: merge with ResBlock1 (lmxue, yicheng)
class ResBlock1_vits(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(ResBlock1_vits, self).__init__()
        self.convs1 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[2],
                        padding=get_padding(kernel_size, dilation[2]),
                    )
                ),
            ]
        )
        self.convs1.apply(init_weights)

        self.convs2 = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=1,
                        padding=get_padding(kernel_size, 1),
                    )
                ),
            ]
        )
        self.convs2.apply(init_weights)

    def forward(self, x, x_mask=None):
        for c1, c2 in zip(self.convs1, self.convs2):
            xt = F.leaky_relu(x, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c1(xt)
            xt = F.leaky_relu(xt, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c2(xt)
            x = xt + x
        if x_mask is not None:
            x = x * x_mask
        return x

    def remove_weight_norm(self):
        for l in self.convs1:
            remove_weight_norm(l)
        for l in self.convs2:
            remove_weight_norm(l)


# todo: merge with ResBlock2 (lmxue, yicheng)
class ResBlock2_vits(torch.nn.Module):
    def __init__(self, channels, kernel_size=3, dilation=(1, 3)):
        super(ResBlock2_vits, self).__init__()
        self.convs = nn.ModuleList(
            [
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[0],
                        padding=get_padding(kernel_size, dilation[0]),
                    )
                ),
                weight_norm(
                    Conv1d(
                        channels,
                        channels,
                        kernel_size,
                        1,
                        dilation=dilation[1],
                        padding=get_padding(kernel_size, dilation[1]),
                    )
                ),
            ]
        )
        self.convs.apply(init_weights)

    def forward(self, x, x_mask=None):
        for c in self.convs:
            xt = F.leaky_relu(x, LRELU_SLOPE)
            if x_mask is not None:
                xt = xt * x_mask
            xt = c(xt)
            x = xt + x
        if x_mask is not None:
            x = x * x_mask
        return x

    def remove_weight_norm(self):
        for l in self.convs:
            remove_weight_norm(l)


# todo: merge with HiFiGAN (lmxue, yicheng)
class HiFiGAN_vits(torch.nn.Module):
    def __init__(
        self,
        initial_channel,
        resblock,
        resblock_kernel_sizes,
        resblock_dilation_sizes,
        upsample_rates,
        upsample_initial_channel,
        upsample_kernel_sizes,
        gin_channels=0,
    ):
        super(HiFiGAN_vits, self).__init__()
        self.num_kernels = len(resblock_kernel_sizes)
        self.num_upsamples = len(upsample_rates)
        self.conv_pre = Conv1d(
            initial_channel, upsample_initial_channel, 7, 1, padding=3
        )
        resblock = ResBlock1_vits if resblock == "1" else ResBlock2_vits

        self.ups = nn.ModuleList()
        for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
            self.ups.append(
                weight_norm(
                    ConvTranspose1d(
                        upsample_initial_channel // (2**i),
                        upsample_initial_channel // (2 ** (i + 1)),
                        k,
                        u,
                        padding=(k - u) // 2,
                    )
                )
            )

        self.resblocks = nn.ModuleList()
        for i in range(len(self.ups)):
            ch = upsample_initial_channel // (2 ** (i + 1))
            for j, (k, d) in enumerate(
                zip(resblock_kernel_sizes, resblock_dilation_sizes)
            ):
                self.resblocks.append(resblock(ch, k, d))

        self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
        self.ups.apply(init_weights)

        if gin_channels != 0:
            self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)

    def forward(self, x, g=None):
        x = self.conv_pre(x)
        if g is not None:
            x = x + self.cond(g)

        for i in range(self.num_upsamples):
            x = F.leaky_relu(x, LRELU_SLOPE)
            x = self.ups[i](x)
            xs = None
            for j in range(self.num_kernels):
                if xs is None:
                    xs = self.resblocks[i * self.num_kernels + j](x)
                else:
                    xs += self.resblocks[i * self.num_kernels + j](x)
            x = xs / self.num_kernels
        x = F.leaky_relu(x)
        x = self.conv_post(x)
        x = torch.tanh(x)

        return x

    def remove_weight_norm(self):
        for l in self.ups:
            remove_weight_norm(l)
        for l in self.resblocks:
            l.remove_weight_norm()