voice-changer/server/voice_changer/MMVCv13/models/models.py

import torch
from torch import nn
from torch.nn import functional as F

from .modules import ResidualCouplingLayer, Flip, WN, ResBlock1, ResBlock2, LRELU_SLOPE


from torch.nn import Conv1d, ConvTranspose1d
from torch.nn.utils import weight_norm, remove_weight_norm
from .commons import init_weights, sequence_mask


class ResidualCouplingBlock(nn.Module):
    def __init__(self, channels, hidden_channels, kernel_size, dilation_rate, n_layers, n_flows=4, gin_channels=0):
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.n_flows = n_flows
        self.gin_channels = gin_channels

        self.flows = nn.ModuleList()
        for i in range(n_flows):
            self.flows.append(ResidualCouplingLayer(channels, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels, mean_only=True))
            self.flows.append(Flip())

    def forward(self, x, x_mask, g=None, reverse=False):
        if not reverse:
            for flow in self.flows:
                x, _ = flow(x, x_mask, g=g, reverse=reverse)
        else:
            for flow in reversed(self.flows):
                x = flow(x, x_mask, g=g, reverse=reverse)
        return x


class PosteriorEncoder(nn.Module):
    def __init__(self, in_channels, out_channels, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=0):
        super().__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.gin_channels = gin_channels

        self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
        self.enc = WN(hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels)
        self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
        # self.randn = torch.randn(1, 1, 1) # ダミーで初期化

    def forward(self, x, x_lengths, g=None):
        x_mask = torch.unsqueeze(sequence_mask(x_lengths, x.size(2)), 1).to(x.dtype)
        x = self.pre(x) * x_mask
        x = self.enc(x, x_mask, g=g)
        stats = self.proj(x) * x_mask
        m, logs = torch.split(stats, self.out_channels, dim=1)
        # if self.randn.size() != m.size(): # m の形が違う時だけ生成
        self.randn = torch.randn_like(m)
        z = (m + self.randn * torch.exp(logs)) * x_mask
        return z, m, logs, x_mask


class Generator(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(Generator, 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 if resblock == "1" else ResBlock2

        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)
            gin_channels = 0

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

        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()


class SynthesizerTrn(nn.Module):
    """
    Synthesizer for Training
    """

    def __init__(self, n_vocab, spec_channels, segment_size, inter_channels, hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout, resblock, resblock_kernel_sizes, resblock_dilation_sizes, upsample_rates, upsample_initial_channel, upsample_kernel_sizes, n_flow, n_speakers=0, gin_channels=0, use_sdp=True, **kwargs):
        super().__init__()
        self.n_vocab = n_vocab
        self.spec_channels = spec_channels
        self.hidden_channels = hidden_channels
        self.filter_channels = filter_channels
        self.n_heads = n_heads
        self.n_layers = n_layers
        self.kernel_size = kernel_size
        self.p_dropout = p_dropout
        self.resblock = resblock
        self.resblock_kernel_sizes = resblock_kernel_sizes
        self.resblock_dilation_sizes = resblock_dilation_sizes
        self.upsample_rates = upsample_rates
        self.upsample_initial_channel = upsample_initial_channel
        self.upsample_kernel_sizes = upsample_kernel_sizes
        self.segment_size = segment_size
        self.n_speakers = n_speakers
        self.gin_channels = gin_channels
        self.use_sdp = use_sdp

        self.dec = Generator(inter_channels, resblock, resblock_kernel_sizes, resblock_dilation_sizes, upsample_rates, upsample_initial_channel, upsample_kernel_sizes, gin_channels=gin_channels)
        self.enc_q = PosteriorEncoder(spec_channels, inter_channels, hidden_channels, 5, 1, 16, gin_channels=gin_channels)
        self.flow = ResidualCouplingBlock(inter_channels, hidden_channels, 5, 1, 4, n_flows=n_flow, gin_channels=gin_channels)

        if n_speakers > 1:
            self.emb_g = nn.Embedding(n_speakers, gin_channels)

    def forward(self, y, y_lengths, sid_src, sid_tgt):
        return self.voice_conversion(y, y_lengths, sid_src, sid_tgt)

    def voice_conversion(self, y, y_lengths, sid_src, sid_tgt):
        assert self.n_speakers > 0, "n_speakers have to be larger than 0."
        g_src = self.emb_g(sid_src).unsqueeze(-1)
        g_tgt = self.emb_g(sid_tgt).unsqueeze(-1)
        z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g_src)
        z_p = self.flow(z, y_mask, g=g_src)
        z_hat = self.flow(z_p, y_mask, g=g_tgt, reverse=True)
        o_hat = self.dec(z_hat * y_mask, g=g_tgt)
        return o_hat