File size: 23,806 Bytes
3c7a160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
import math
import torch
from torch import nn
from torch.nn import functional as F

from module import commons
from module.modules import LayerNorm


class Encoder(nn.Module):
    def __init__(
        self,
        hidden_channels,
        filter_channels,
        n_heads,
        n_layers,
        kernel_size=1,
        p_dropout=0.0,
        window_size=4,
        isflow=False,
        **kwargs
    ):
        super().__init__()
        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.window_size = window_size

        self.drop = nn.Dropout(p_dropout)
        self.attn_layers = nn.ModuleList()
        self.norm_layers_1 = nn.ModuleList()
        self.ffn_layers = nn.ModuleList()
        self.norm_layers_2 = nn.ModuleList()
        for i in range(self.n_layers):
            self.attn_layers.append(
                MultiHeadAttention(
                    hidden_channels,
                    hidden_channels,
                    n_heads,
                    p_dropout=p_dropout,
                    window_size=window_size,
                )
            )
            self.norm_layers_1.append(LayerNorm(hidden_channels))
            self.ffn_layers.append(
                FFN(
                    hidden_channels,
                    hidden_channels,
                    filter_channels,
                    kernel_size,
                    p_dropout=p_dropout,
                )
            )
            self.norm_layers_2.append(LayerNorm(hidden_channels))
        if isflow:
            cond_layer = torch.nn.Conv1d(
                kwargs["gin_channels"], 2 * hidden_channels * n_layers, 1
            )
            self.cond_pre = torch.nn.Conv1d(hidden_channels, 2 * hidden_channels, 1)
            self.cond_layer = weight_norm_modules(cond_layer, name="weight")
            self.gin_channels = kwargs["gin_channels"]

    def forward(self, x, x_mask, g=None):
        attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
        x = x * x_mask
        if g is not None:
            g = self.cond_layer(g)

        for i in range(self.n_layers):
            if g is not None:
                x = self.cond_pre(x)
                cond_offset = i * 2 * self.hidden_channels
                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
                x = commons.fused_add_tanh_sigmoid_multiply(
                    x, g_l, torch.IntTensor([self.hidden_channels])
                )
            y = self.attn_layers[i](x, x, attn_mask)
            y = self.drop(y)
            x = self.norm_layers_1[i](x + y)

            y = self.ffn_layers[i](x, x_mask)
            y = self.drop(y)
            x = self.norm_layers_2[i](x + y)
        x = x * x_mask
        return x


class Decoder(nn.Module):
    def __init__(
        self,
        hidden_channels,
        filter_channels,
        n_heads,
        n_layers,
        kernel_size=1,
        p_dropout=0.0,
        proximal_bias=False,
        proximal_init=True,
        **kwargs
    ):
        super().__init__()
        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.proximal_bias = proximal_bias
        self.proximal_init = proximal_init

        self.drop = nn.Dropout(p_dropout)
        self.self_attn_layers = nn.ModuleList()
        self.norm_layers_0 = nn.ModuleList()
        self.encdec_attn_layers = nn.ModuleList()
        self.norm_layers_1 = nn.ModuleList()
        self.ffn_layers = nn.ModuleList()
        self.norm_layers_2 = nn.ModuleList()
        for i in range(self.n_layers):
            self.self_attn_layers.append(
                MultiHeadAttention(
                    hidden_channels,
                    hidden_channels,
                    n_heads,
                    p_dropout=p_dropout,
                    proximal_bias=proximal_bias,
                    proximal_init=proximal_init,
                )
            )
            self.norm_layers_0.append(LayerNorm(hidden_channels))
            self.encdec_attn_layers.append(
                MultiHeadAttention(
                    hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout
                )
            )
            self.norm_layers_1.append(LayerNorm(hidden_channels))
            self.ffn_layers.append(
                FFN(
                    hidden_channels,
                    hidden_channels,
                    filter_channels,
                    kernel_size,
                    p_dropout=p_dropout,
                    causal=True,
                )
            )
            self.norm_layers_2.append(LayerNorm(hidden_channels))

    def forward(self, x, x_mask, h, h_mask):
        """
        x: decoder input
        h: encoder output
        """
        self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(
            device=x.device, dtype=x.dtype
        )
        encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
        x = x * x_mask
        for i in range(self.n_layers):
            y = self.self_attn_layers[i](x, x, self_attn_mask)
            y = self.drop(y)
            x = self.norm_layers_0[i](x + y)

            y = self.encdec_attn_layers[i](x, h, encdec_attn_mask)
            y = self.drop(y)
            x = self.norm_layers_1[i](x + y)

            y = self.ffn_layers[i](x, x_mask)
            y = self.drop(y)
            x = self.norm_layers_2[i](x + y)
        x = x * x_mask
        return x


class MultiHeadAttention(nn.Module):
    def __init__(
        self,
        channels,
        out_channels,
        n_heads,
        p_dropout=0.0,
        window_size=None,
        heads_share=True,
        block_length=None,
        proximal_bias=False,
        proximal_init=False,
    ):
        super().__init__()
        assert channels % n_heads == 0

        self.channels = channels
        self.out_channels = out_channels
        self.n_heads = n_heads
        self.p_dropout = p_dropout
        self.window_size = window_size
        self.heads_share = heads_share
        self.block_length = block_length
        self.proximal_bias = proximal_bias
        self.proximal_init = proximal_init
        self.attn = None

        self.k_channels = channels // n_heads
        self.conv_q = nn.Conv1d(channels, channels, 1)
        self.conv_k = nn.Conv1d(channels, channels, 1)
        self.conv_v = nn.Conv1d(channels, channels, 1)
        self.conv_o = nn.Conv1d(channels, out_channels, 1)
        self.drop = nn.Dropout(p_dropout)

        if window_size is not None:
            n_heads_rel = 1 if heads_share else n_heads
            rel_stddev = self.k_channels**-0.5
            self.emb_rel_k = nn.Parameter(
                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
                * rel_stddev
            )
            self.emb_rel_v = nn.Parameter(
                torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels)
                * rel_stddev
            )

        nn.init.xavier_uniform_(self.conv_q.weight)
        nn.init.xavier_uniform_(self.conv_k.weight)
        nn.init.xavier_uniform_(self.conv_v.weight)
        if proximal_init:
            with torch.no_grad():
                self.conv_k.weight.copy_(self.conv_q.weight)
                self.conv_k.bias.copy_(self.conv_q.bias)

    def forward(self, x, c, attn_mask=None):
        q = self.conv_q(x)
        k = self.conv_k(c)
        v = self.conv_v(c)

        x, self.attn = self.attention(q, k, v, mask=attn_mask)

        x = self.conv_o(x)
        return x

    def attention(self, query, key, value, mask=None):
        # reshape [b, d, t] -> [b, n_h, t, d_k]
        b, d, t_s, t_t = (*key.size(), query.size(2))
        query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3)
        key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
        value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)

        scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1))
        if self.window_size is not None:
            assert (
                t_s == t_t
            ), "Relative attention is only available for self-attention."
            key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s)
            rel_logits = self._matmul_with_relative_keys(
                query / math.sqrt(self.k_channels), key_relative_embeddings
            )
            scores_local = self._relative_position_to_absolute_position(rel_logits)
            scores = scores + scores_local
        if self.proximal_bias:
            assert t_s == t_t, "Proximal bias is only available for self-attention."
            scores = scores + self._attention_bias_proximal(t_s).to(
                device=scores.device, dtype=scores.dtype
            )
        if mask is not None:
            scores = scores.masked_fill(mask == 0, -1e4)
            if self.block_length is not None:
                assert (
                    t_s == t_t
                ), "Local attention is only available for self-attention."
                block_mask = (
                    torch.ones_like(scores)
                    .triu(-self.block_length)
                    .tril(self.block_length)
                )
                scores = scores.masked_fill(block_mask == 0, -1e4)
        p_attn = F.softmax(scores, dim=-1)  # [b, n_h, t_t, t_s]
        p_attn = self.drop(p_attn)
        output = torch.matmul(p_attn, value)
        if self.window_size is not None:
            relative_weights = self._absolute_position_to_relative_position(p_attn)
            value_relative_embeddings = self._get_relative_embeddings(
                self.emb_rel_v, t_s
            )
            output = output + self._matmul_with_relative_values(
                relative_weights, value_relative_embeddings
            )
        output = (
            output.transpose(2, 3).contiguous().view(b, d, t_t)
        )  # [b, n_h, t_t, d_k] -> [b, d, t_t]
        return output, p_attn

    def _matmul_with_relative_values(self, x, y):
        """
        x: [b, h, l, m]
        y: [h or 1, m, d]
        ret: [b, h, l, d]
        """
        ret = torch.matmul(x, y.unsqueeze(0))
        return ret

    def _matmul_with_relative_keys(self, x, y):
        """
        x: [b, h, l, d]
        y: [h or 1, m, d]
        ret: [b, h, l, m]
        """
        ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1))
        return ret

    def _get_relative_embeddings(self, relative_embeddings, length):
        max_relative_position = 2 * self.window_size + 1
        # Pad first before slice to avoid using cond ops.
        pad_length = max(length - (self.window_size + 1), 0)
        slice_start_position = max((self.window_size + 1) - length, 0)
        slice_end_position = slice_start_position + 2 * length - 1
        if pad_length > 0:
            padded_relative_embeddings = F.pad(
                relative_embeddings,
                commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]),
            )
        else:
            padded_relative_embeddings = relative_embeddings
        used_relative_embeddings = padded_relative_embeddings[
            :, slice_start_position:slice_end_position
        ]
        return used_relative_embeddings

    def _relative_position_to_absolute_position(self, x):
        """
        x: [b, h, l, 2*l-1]
        ret: [b, h, l, l]
        """
        batch, heads, length, _ = x.size()
        # Concat columns of pad to shift from relative to absolute indexing.
        x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, 1]]))

        # Concat extra elements so to add up to shape (len+1, 2*len-1).
        x_flat = x.view([batch, heads, length * 2 * length])
        x_flat = F.pad(
            x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [0, length - 1]])
        )

        # Reshape and slice out the padded elements.
        x_final = x_flat.view([batch, heads, length + 1, 2 * length - 1])[
            :, :, :length, length - 1 :
        ]
        return x_final

    def _absolute_position_to_relative_position(self, x):
        """
        x: [b, h, l, l]
        ret: [b, h, l, 2*l-1]
        """
        batch, heads, length, _ = x.size()
        # padd along column
        x = F.pad(
            x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length - 1]])
        )
        x_flat = x.view([batch, heads, length**2 + length * (length - 1)])
        # add 0's in the beginning that will skew the elements after reshape
        x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]]))
        x_final = x_flat.view([batch, heads, length, 2 * length])[:, :, :, 1:]
        return x_final

    def _attention_bias_proximal(self, length):
        """Bias for self-attention to encourage attention to close positions.
        Args:
          length: an integer scalar.
        Returns:
          a Tensor with shape [1, 1, length, length]
        """
        r = torch.arange(length, dtype=torch.float32)
        diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1)
        return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0)


class FFN(nn.Module):
    def __init__(
        self,
        in_channels,
        out_channels,
        filter_channels,
        kernel_size,
        p_dropout=0.0,
        activation=None,
        causal=False,
    ):
        super().__init__()
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.filter_channels = filter_channels
        self.kernel_size = kernel_size
        self.p_dropout = p_dropout
        self.activation = activation
        self.causal = causal

        if causal:
            self.padding = self._causal_padding
        else:
            self.padding = self._same_padding

        self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size)
        self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size)
        self.drop = nn.Dropout(p_dropout)

    def forward(self, x, x_mask):
        x = self.conv_1(self.padding(x * x_mask))
        if self.activation == "gelu":
            x = x * torch.sigmoid(1.702 * x)
        else:
            x = torch.relu(x)
        x = self.drop(x)
        x = self.conv_2(self.padding(x * x_mask))
        return x * x_mask

    def _causal_padding(self, x):
        if self.kernel_size == 1:
            return x
        pad_l = self.kernel_size - 1
        pad_r = 0
        padding = [[0, 0], [0, 0], [pad_l, pad_r]]
        x = F.pad(x, commons.convert_pad_shape(padding))
        return x

    def _same_padding(self, x):
        if self.kernel_size == 1:
            return x
        pad_l = (self.kernel_size - 1) // 2
        pad_r = self.kernel_size // 2
        padding = [[0, 0], [0, 0], [pad_l, pad_r]]
        x = F.pad(x, commons.convert_pad_shape(padding))
        return x


import torch.nn as nn
from torch.nn.utils import remove_weight_norm, weight_norm


class Depthwise_Separable_Conv1D(nn.Module):
    def __init__(
        self,
        in_channels,
        out_channels,
        kernel_size,
        stride=1,
        padding=0,
        dilation=1,
        bias=True,
        padding_mode="zeros",  # TODO: refine this type
        device=None,
        dtype=None,
    ):
        super().__init__()
        self.depth_conv = nn.Conv1d(
            in_channels=in_channels,
            out_channels=in_channels,
            kernel_size=kernel_size,
            groups=in_channels,
            stride=stride,
            padding=padding,
            dilation=dilation,
            bias=bias,
            padding_mode=padding_mode,
            device=device,
            dtype=dtype,
        )
        self.point_conv = nn.Conv1d(
            in_channels=in_channels,
            out_channels=out_channels,
            kernel_size=1,
            bias=bias,
            device=device,
            dtype=dtype,
        )

    def forward(self, input):
        return self.point_conv(self.depth_conv(input))

    def weight_norm(self):
        self.depth_conv = weight_norm(self.depth_conv, name="weight")
        self.point_conv = weight_norm(self.point_conv, name="weight")

    def remove_weight_norm(self):
        self.depth_conv = remove_weight_norm(self.depth_conv, name="weight")
        self.point_conv = remove_weight_norm(self.point_conv, name="weight")


class Depthwise_Separable_TransposeConv1D(nn.Module):
    def __init__(
        self,
        in_channels,
        out_channels,
        kernel_size,
        stride=1,
        padding=0,
        output_padding=0,
        bias=True,
        dilation=1,
        padding_mode="zeros",  # TODO: refine this type
        device=None,
        dtype=None,
    ):
        super().__init__()
        self.depth_conv = nn.ConvTranspose1d(
            in_channels=in_channels,
            out_channels=in_channels,
            kernel_size=kernel_size,
            groups=in_channels,
            stride=stride,
            output_padding=output_padding,
            padding=padding,
            dilation=dilation,
            bias=bias,
            padding_mode=padding_mode,
            device=device,
            dtype=dtype,
        )
        self.point_conv = nn.Conv1d(
            in_channels=in_channels,
            out_channels=out_channels,
            kernel_size=1,
            bias=bias,
            device=device,
            dtype=dtype,
        )

    def forward(self, input):
        return self.point_conv(self.depth_conv(input))

    def weight_norm(self):
        self.depth_conv = weight_norm(self.depth_conv, name="weight")
        self.point_conv = weight_norm(self.point_conv, name="weight")

    def remove_weight_norm(self):
        remove_weight_norm(self.depth_conv, name="weight")
        remove_weight_norm(self.point_conv, name="weight")


def weight_norm_modules(module, name="weight", dim=0):
    if isinstance(module, Depthwise_Separable_Conv1D) or isinstance(
        module, Depthwise_Separable_TransposeConv1D
    ):
        module.weight_norm()
        return module
    else:
        return weight_norm(module, name, dim)


def remove_weight_norm_modules(module, name="weight"):
    if isinstance(module, Depthwise_Separable_Conv1D) or isinstance(
        module, Depthwise_Separable_TransposeConv1D
    ):
        module.remove_weight_norm()
    else:
        remove_weight_norm(module, name)


class FFT(nn.Module):
    def __init__(
        self,
        hidden_channels,
        filter_channels,
        n_heads,
        n_layers=1,
        kernel_size=1,
        p_dropout=0.0,
        proximal_bias=False,
        proximal_init=True,
        isflow=False,
        **kwargs
    ):
        super().__init__()
        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.proximal_bias = proximal_bias
        self.proximal_init = proximal_init
        if isflow:
            cond_layer = torch.nn.Conv1d(
                kwargs["gin_channels"], 2 * hidden_channels * n_layers, 1
            )
            self.cond_pre = torch.nn.Conv1d(hidden_channels, 2 * hidden_channels, 1)
            self.cond_layer = weight_norm_modules(cond_layer, name="weight")
            self.gin_channels = kwargs["gin_channels"]
        self.drop = nn.Dropout(p_dropout)
        self.self_attn_layers = nn.ModuleList()
        self.norm_layers_0 = nn.ModuleList()
        self.ffn_layers = nn.ModuleList()
        self.norm_layers_1 = nn.ModuleList()
        for i in range(self.n_layers):
            self.self_attn_layers.append(
                MultiHeadAttention(
                    hidden_channels,
                    hidden_channels,
                    n_heads,
                    p_dropout=p_dropout,
                    proximal_bias=proximal_bias,
                    proximal_init=proximal_init,
                )
            )
            self.norm_layers_0.append(LayerNorm(hidden_channels))
            self.ffn_layers.append(
                FFN(
                    hidden_channels,
                    hidden_channels,
                    filter_channels,
                    kernel_size,
                    p_dropout=p_dropout,
                    causal=True,
                )
            )
            self.norm_layers_1.append(LayerNorm(hidden_channels))

    def forward(self, x, x_mask, g=None):
        """
        x: decoder input
        h: encoder output
        """
        if g is not None:
            g = self.cond_layer(g)

        self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(
            device=x.device, dtype=x.dtype
        )
        x = x * x_mask
        for i in range(self.n_layers):
            if g is not None:
                x = self.cond_pre(x)
                cond_offset = i * 2 * self.hidden_channels
                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
                x = commons.fused_add_tanh_sigmoid_multiply(
                    x, g_l, torch.IntTensor([self.hidden_channels])
                )
            y = self.self_attn_layers[i](x, x, self_attn_mask)
            y = self.drop(y)
            x = self.norm_layers_0[i](x + y)

            y = self.ffn_layers[i](x, x_mask)
            y = self.drop(y)
            x = self.norm_layers_1[i](x + y)
        x = x * x_mask
        return x


class TransformerCouplingLayer(nn.Module):
    def __init__(
        self,
        channels,
        hidden_channels,
        kernel_size,
        n_layers,
        n_heads,
        p_dropout=0,
        filter_channels=0,
        mean_only=False,
        wn_sharing_parameter=None,
        gin_channels=0,
    ):
        assert channels % 2 == 0, "channels should be divisible by 2"
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.half_channels = channels // 2
        self.mean_only = mean_only

        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
        self.enc = (
            Encoder(
                hidden_channels,
                filter_channels,
                n_heads,
                n_layers,
                kernel_size,
                p_dropout,
                isflow=True,
                gin_channels=gin_channels,
            )
            if wn_sharing_parameter is None
            else wn_sharing_parameter
        )
        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
        self.post.weight.data.zero_()
        self.post.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0) * x_mask
        h = self.enc(h, x_mask, g=g)
        stats = self.post(h) * x_mask
        if not self.mean_only:
            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
        else:
            m = stats
            logs = torch.zeros_like(m)

        if not reverse:
            x1 = m + x1 * torch.exp(logs) * x_mask
            x = torch.cat([x0, x1], 1)
            logdet = torch.sum(logs, [1, 2])
            return x, logdet
        else:
            x1 = (x1 - m) * torch.exp(-logs) * x_mask
            x = torch.cat([x0, x1], 1)
            return x