File size: 13,847 Bytes
26925fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
import torch
import torch.nn.functional as F
import torch.nn as nn
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm

from modules.parallel_wavegan.layers import UpsampleNetwork, ConvInUpsampleNetwork
from modules.parallel_wavegan.models.source import SourceModuleHnNSF
import numpy as np

LRELU_SLOPE = 0.1


def init_weights(m, mean=0.0, std=0.01):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        m.weight.data.normal_(mean, std)


def apply_weight_norm(m):
    classname = m.__class__.__name__
    if classname.find("Conv") != -1:
        weight_norm(m)


def get_padding(kernel_size, dilation=1):
    return int((kernel_size * dilation - dilation) / 2)


class ResBlock1(torch.nn.Module):
    def __init__(self, h, channels, kernel_size=3, dilation=(1, 3, 5)):
        super(ResBlock1, self).__init__()
        self.h = h
        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, h, channels, kernel_size=3, dilation=(1, 3)):
        super(ResBlock2, self).__init__()
        self.h = h
        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 Conv1d1x1(Conv1d):
    """1x1 Conv1d with customized initialization."""

    def __init__(self, in_channels, out_channels, bias):
        """Initialize 1x1 Conv1d module."""
        super(Conv1d1x1, self).__init__(in_channels, out_channels,
                                        kernel_size=1, padding=0,
                                        dilation=1, bias=bias)


class HifiGanGenerator(torch.nn.Module):
    def __init__(self, h, c_out=1):
        super(HifiGanGenerator, self).__init__()
        self.h = h
        self.num_kernels = len(h['resblock_kernel_sizes'])
        self.num_upsamples = len(h['upsample_rates'])

        if h['use_pitch_embed']:
            self.harmonic_num = 8
            self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(h['upsample_rates']))
            self.m_source = SourceModuleHnNSF(
                sampling_rate=h['audio_sample_rate'],
                harmonic_num=self.harmonic_num)
            self.noise_convs = nn.ModuleList()
        self.conv_pre = weight_norm(Conv1d(80, h['upsample_initial_channel'], 7, 1, padding=3))
        resblock = ResBlock1 if h['resblock'] == '1' else ResBlock2

        self.ups = nn.ModuleList()
        for i, (u, k) in enumerate(zip(h['upsample_rates'], h['upsample_kernel_sizes'])):
            c_cur = h['upsample_initial_channel'] // (2 ** (i + 1))
            self.ups.append(weight_norm(
                ConvTranspose1d(c_cur * 2, c_cur, k, u, padding=(k - u) // 2)))
            if h['use_pitch_embed']:
                if i + 1 < len(h['upsample_rates']):
                    stride_f0 = np.prod(h['upsample_rates'][i + 1:])
                    self.noise_convs.append(Conv1d(
                        1, c_cur, kernel_size=stride_f0 * 2, stride=stride_f0, padding=stride_f0 // 2))
                else:
                    self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))

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

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

    def forward(self, x, f0=None):
        if f0 is not None:
            # harmonic-source signal, noise-source signal, uv flag
            f0 = self.f0_upsamp(f0[:, None]).transpose(1, 2)
            har_source, noi_source, uv = self.m_source(f0)
            har_source = har_source.transpose(1, 2)

        x = self.conv_pre(x)
        for i in range(self.num_upsamples):
            x = F.leaky_relu(x, LRELU_SLOPE)
            x = self.ups[i](x)
            if f0 is not None:
                x_source = self.noise_convs[i](har_source)
                x_source = torch.nn.functional.relu(x_source)
                tmp_shape = x_source.shape[1]
                x_source = torch.nn.functional.layer_norm(x_source.transpose(1, -1), (tmp_shape, )).transpose(1, -1)
                x = x + x_source
            xs = None
            for j in range(self.num_kernels):
                xs_ = self.resblocks[i * self.num_kernels + j](x)
                if xs is None:
                    xs = xs_
                else:
                    xs += xs_
            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)


class DiscriminatorP(torch.nn.Module):
    def __init__(self, period, kernel_size=5, stride=3, use_spectral_norm=False, use_cond=False, c_in=1):
        super(DiscriminatorP, self).__init__()
        self.use_cond = use_cond
        if use_cond:
            from utils.hparams import hparams
            t = hparams['hop_size']
            self.cond_net = torch.nn.ConvTranspose1d(80, 1, t * 2, stride=t, padding=t // 2)
            c_in = 2

        self.period = period
        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
        self.convs = nn.ModuleList([
            norm_f(Conv2d(c_in, 32, (kernel_size, 1), (stride, 1), padding=(get_padding(5, 1), 0))),
            norm_f(Conv2d(32, 128, (kernel_size, 1), (stride, 1), padding=(get_padding(5, 1), 0))),
            norm_f(Conv2d(128, 512, (kernel_size, 1), (stride, 1), padding=(get_padding(5, 1), 0))),
            norm_f(Conv2d(512, 1024, (kernel_size, 1), (stride, 1), padding=(get_padding(5, 1), 0))),
            norm_f(Conv2d(1024, 1024, (kernel_size, 1), 1, padding=(2, 0))),
        ])
        self.conv_post = norm_f(Conv2d(1024, 1, (3, 1), 1, padding=(1, 0)))

    def forward(self, x, mel):
        fmap = []
        if self.use_cond:
            x_mel = self.cond_net(mel)
            x = torch.cat([x_mel, x], 1)
        # 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, 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_cond=False, c_in=1):
        super(MultiPeriodDiscriminator, self).__init__()
        self.discriminators = nn.ModuleList([
            DiscriminatorP(2, use_cond=use_cond, c_in=c_in),
            DiscriminatorP(3, use_cond=use_cond, c_in=c_in),
            DiscriminatorP(5, use_cond=use_cond, c_in=c_in),
            DiscriminatorP(7, use_cond=use_cond, c_in=c_in),
            DiscriminatorP(11, use_cond=use_cond, c_in=c_in),
        ])

    def forward(self, y, y_hat, mel=None):
        y_d_rs = []
        y_d_gs = []
        fmap_rs = []
        fmap_gs = []
        for i, d in enumerate(self.discriminators):
            y_d_r, fmap_r = d(y, mel)
            y_d_g, fmap_g = d(y_hat, mel)
            y_d_rs.append(y_d_r)
            fmap_rs.append(fmap_r)
            y_d_gs.append(y_d_g)
            fmap_gs.append(fmap_g)

        return y_d_rs, y_d_gs, fmap_rs, fmap_gs


class DiscriminatorS(torch.nn.Module):
    def __init__(self, use_spectral_norm=False, use_cond=False, upsample_rates=None, c_in=1):
        super(DiscriminatorS, self).__init__()
        self.use_cond = use_cond
        if use_cond:
            t = np.prod(upsample_rates)
            self.cond_net = torch.nn.ConvTranspose1d(80, 1, t * 2, stride=t, padding=t // 2)
            c_in = 2
        norm_f = weight_norm if use_spectral_norm == False else spectral_norm
        self.convs = nn.ModuleList([
            norm_f(Conv1d(c_in, 128, 15, 1, padding=7)),
            norm_f(Conv1d(128, 128, 41, 2, groups=4, padding=20)),
            norm_f(Conv1d(128, 256, 41, 2, groups=16, padding=20)),
            norm_f(Conv1d(256, 512, 41, 4, groups=16, padding=20)),
            norm_f(Conv1d(512, 1024, 41, 4, groups=16, padding=20)),
            norm_f(Conv1d(1024, 1024, 41, 1, groups=16, 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, mel):
        if self.use_cond:
            x_mel = self.cond_net(mel)
            x = torch.cat([x_mel, x], 1)
        fmap = []
        for l in self.convs:
            x = l(x)
            x = F.leaky_relu(x, LRELU_SLOPE)
            fmap.append(x)
        x = self.conv_post(x)
        fmap.append(x)
        x = torch.flatten(x, 1, -1)

        return x, fmap


class MultiScaleDiscriminator(torch.nn.Module):
    def __init__(self, use_cond=False, c_in=1):
        super(MultiScaleDiscriminator, self).__init__()
        from utils.hparams import hparams
        self.discriminators = nn.ModuleList([
            DiscriminatorS(use_spectral_norm=True, use_cond=use_cond,
                           upsample_rates=[4, 4, hparams['hop_size'] // 16],
                           c_in=c_in),
            DiscriminatorS(use_cond=use_cond,
                           upsample_rates=[4, 4, hparams['hop_size'] // 32],
                           c_in=c_in),
            DiscriminatorS(use_cond=use_cond,
                           upsample_rates=[4, 4, hparams['hop_size'] // 64],
                           c_in=c_in),
        ])
        self.meanpools = nn.ModuleList([
            AvgPool1d(4, 2, padding=1),
            AvgPool1d(4, 2, padding=1)
        ])

    def forward(self, y, y_hat, mel=None):
        y_d_rs = []
        y_d_gs = []
        fmap_rs = []
        fmap_gs = []
        for i, d in enumerate(self.discriminators):
            if i != 0:
                y = self.meanpools[i - 1](y)
                y_hat = self.meanpools[i - 1](y_hat)
            y_d_r, fmap_r = d(y, mel)
            y_d_g, fmap_g = d(y_hat, mel)
            y_d_rs.append(y_d_r)
            fmap_rs.append(fmap_r)
            y_d_gs.append(y_d_g)
            fmap_gs.append(fmap_g)

        return y_d_rs, y_d_gs, fmap_rs, fmap_gs


def feature_loss(fmap_r, fmap_g):
    loss = 0
    for dr, dg in zip(fmap_r, fmap_g):
        for rl, gl in zip(dr, dg):
            loss += torch.mean(torch.abs(rl - gl))

    return loss * 2


def discriminator_loss(disc_real_outputs, disc_generated_outputs):
    r_losses = 0
    g_losses = 0
    for dr, dg in zip(disc_real_outputs, disc_generated_outputs):
        r_loss = torch.mean((1 - dr) ** 2)
        g_loss = torch.mean(dg ** 2)
        r_losses += r_loss
        g_losses += g_loss
    r_losses = r_losses / len(disc_real_outputs)
    g_losses = g_losses / len(disc_real_outputs)
    return r_losses, g_losses


def cond_discriminator_loss(outputs):
    loss = 0
    for dg in outputs:
        g_loss = torch.mean(dg ** 2)
        loss += g_loss
    loss = loss / len(outputs)
    return loss


def generator_loss(disc_outputs):
    loss = 0
    for dg in disc_outputs:
        l = torch.mean((1 - dg) ** 2)
        loss += l
    loss = loss / len(disc_outputs)
    return loss