import torch from torch import nn from torch.nn import Conv1d, ConvTranspose1d, Conv2d from torch.nn import functional as F from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm from sovits import attentions from sovits import commons from sovits import modules from sovits.commons import init_weights, get_padding from sovits.vdecoder.hifigan.hifigan import HifiGanGenerator # import monotonic_align class TextEncoder(nn.Module): def __init__(self, n_vocab, out_channels, hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout): super().__init__() self.n_vocab = n_vocab self.out_channels = out_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.emb = nn.Embedding(n_vocab, hidden_channels) # nn.init.normal_(self.emb.weight, 0.0, hidden_channels**-0.5) self.emb_pitch = nn.Embedding(256, hidden_channels) nn.init.normal_(self.emb_pitch.weight, 0.0, hidden_channels ** -0.5) self.encoder = attentions.Encoder( hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout) self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1) def forward(self, x, x_lengths, pitch): # x = x.transpose(1,2) # x = self.emb(x) * math.sqrt(self.hidden_channels) # [b, t, h] # print(x.shape) x = x + self.emb_pitch(pitch) x = torch.transpose(x, 1, -1) # [b, h, t] x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(x.dtype) x = self.encoder(x * x_mask, x_mask) stats = self.proj(x) * x_mask m, logs = torch.split(stats, self.out_channels, dim=1) return x, m, logs, x_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( modules.ResidualCouplingLayer(channels, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels, mean_only=True)) self.flows.append(modules.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 = modules.WN(hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels) self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1) def forward(self, x, x_lengths, g=None): x_mask = torch.unsqueeze(commons.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) z = (m + torch.randn_like(m) * 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 = modules.ResBlock1 if resblock == '1' else modules.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) 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, modules.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 DiscriminatorP(torch.nn.Module): def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False): super(DiscriminatorP, self).__init__() self.period = period self.use_spectral_norm = use_spectral_norm norm_f = weight_norm if use_spectral_norm == False else spectral_norm self.convs = nn.ModuleList([ norm_f(Conv2d(1, 32, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))), norm_f(Conv2d(32, 128, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))), norm_f(Conv2d(128, 512, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))), norm_f(Conv2d(512, 1024, (kernel_size, 1), (stride, 1), padding=(get_padding(kernel_size, 1), 0))), norm_f(Conv2d(1024, 1024, (kernel_size, 1), 1, padding=(get_padding(kernel_size, 1), 0))), ]) self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0))) def forward(self, x): fmap = [] # 1d to 2d b, c, t = x.shape if t % self.period != 0: # pad first n_pad = self.period - (t % self.period) x = F.pad(x, (0, n_pad), "reflect") t = t + n_pad x = x.view(b, c, t // self.period, self.period) for l in self.convs: x = l(x) x = F.leaky_relu(x, modules.LRELU_SLOPE) fmap.append(x) x = self.conv_post(x) fmap.append(x) x = torch.flatten(x, 1, -1) return x, fmap class DiscriminatorS(torch.nn.Module): def __init__(self, use_spectral_norm=False): super(DiscriminatorS, self).__init__() norm_f = weight_norm if use_spectral_norm == False else spectral_norm self.convs = nn.ModuleList([ norm_f(Conv1d(1, 16, 15, 1, padding=7)), norm_f(Conv1d(16, 64, 41, 4, groups=4, padding=20)), norm_f(Conv1d(64, 256, 41, 4, groups=16, padding=20)), norm_f(Conv1d(256, 1024, 41, 4, groups=64, padding=20)), norm_f(Conv1d(1024, 1024, 41, 4, groups=256, padding=20)), norm_f(Conv1d(1024, 1024, 5, 1, padding=2)), ]) self.conv_post = norm_f(Conv1d(1024, 1, 3, 1, padding=1)) def forward(self, x): fmap = [] for l in self.convs: x = l(x) x = F.leaky_relu(x, modules.LRELU_SLOPE) fmap.append(x) x = self.conv_post(x) fmap.append(x) x = torch.flatten(x, 1, -1) return x, fmap class MultiPeriodDiscriminator(torch.nn.Module): def __init__(self, use_spectral_norm=False): super(MultiPeriodDiscriminator, self).__init__() periods = [2, 3, 5, 7, 11] discs = [DiscriminatorS(use_spectral_norm=use_spectral_norm)] discs = discs + [DiscriminatorP(i, use_spectral_norm=use_spectral_norm) for i in periods] self.discriminators = nn.ModuleList(discs) def forward(self, y, y_hat): y_d_rs = [] y_d_gs = [] fmap_rs = [] fmap_gs = [] for i, d in enumerate(self.discriminators): y_d_r, fmap_r = d(y) y_d_g, fmap_g = d(y_hat) y_d_rs.append(y_d_r) y_d_gs.append(y_d_g) fmap_rs.append(fmap_r) fmap_gs.append(fmap_g) return y_d_rs, y_d_gs, fmap_rs, fmap_gs 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_speakers=0, gin_channels=0, use_sdp=True, **kwargs): super().__init__() self.n_vocab = n_vocab self.spec_channels = spec_channels self.inter_channels = inter_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.enc_p = TextEncoder(n_vocab, inter_channels, hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout) # self.dec = Generator(inter_channels, resblock, resblock_kernel_sizes, resblock_dilation_sizes, upsample_rates, # upsample_initial_channel, upsample_kernel_sizes, gin_channels=gin_channels) # # from DiffSinger: modules.hifigan.hifigan.HifiGanGenerator # hps = { # "resblock_kernel_sizes": [3, 7, 11], # "upsample_rates": [8, 8, 2, 2], # "upsample_initial_channel": 128, # "use_pitch_embed": True, # "audio_sample_rate": kwargs["sampling_rate"], # "resblock": "1", # "resblock_dilation_sizes": [[1, 3, 5], [1, 3, 5], [1, 3, 5]] # } # from sovits json config hps hps = { "resblock_kernel_sizes": resblock_kernel_sizes, "inter_channels": inter_channels, "upsample_rates": upsample_rates, "upsample_kernel_sizes": upsample_kernel_sizes, "upsample_initial_channel": upsample_initial_channel, "use_pitch_embed": True, "audio_sample_rate": kwargs["sampling_rate"], "resblock": "1", "resblock_dilation_sizes": resblock_dilation_sizes } self.dec = HifiGanGenerator(h=hps) 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, gin_channels=gin_channels) if n_speakers > 1: self.emb_g = nn.Embedding(n_speakers, gin_channels) def forward(self, x, x_lengths, y, y_lengths, pitch, sid=None): assert 0 <= y.shape[2] - x.shape[1] * 2 <= 1, (y.shape[2], x.shape[1] * 2, sid) if y.shape[2] != x.shape[1] * 2: y_lengths[y_lengths == y.shape[2]] -= 1 y = y[:, :, :x.shape[1] * 2] x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, pitch) if self.n_speakers > 0: g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1] else: g = None z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=g) z_p = self.flow(z, y_mask, g=g) m_p = torch.repeat_interleave(m_p, repeats=2, dim=2) logs_p = torch.repeat_interleave(logs_p, repeats=2, dim=2) # print(x.shape, y.shape, z.shape, pitch.shape) z_slice, pitch_slice, ids_slice = commons.rand_slice_segments_with_pitch(z, torch.repeat_interleave(pitch, repeats=2, dim=1), y_lengths, self.segment_size) o = self.dec(z_slice, f0=pitch_slice) return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q) def infer(self, x, x_lengths, pitch, sid=None, noise_scale=1, length_scale=1, noise_scale_w=1., max_len=None): x, m_p, logs_p, x_mask = self.enc_p(x, x_lengths, pitch) if self.n_speakers > 0: g = self.emb_g(sid).unsqueeze(-1) # [b, h, 1] else: g = None m_p = torch.repeat_interleave(m_p, repeats=2, dim=2) logs_p = torch.repeat_interleave(logs_p, repeats=2, dim=2) x_mask = torch.repeat_interleave(x_mask, repeats=2, dim=2) z_p = m_p + torch.randn_like(m_p) * torch.exp(logs_p) * noise_scale z = self.flow(z_p, x_mask, g=g, reverse=True) # o = self.dec((z * x_mask)[:, :, :max_len], g=g) # print(x.shape, pitch.shape, sid) # print() o = self.dec((z * x_mask)[:, :, :max_len], f0=torch.repeat_interleave(pitch, repeats=2, dim=1)) return o, x_mask, (z, z_p, m_p, logs_p) 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, y_mask, (z, z_p, z_hat)