File size: 11,056 Bytes
f032e68
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import math
from typing import List
from typing import Union

import numpy as np
import torch
from audiotools import AudioSignal
from audiotools.ml import BaseModel
from torch import nn

from .base import CodecMixin
from ..nn.layers import Snake1d
from ..nn.layers import WNConv1d
from ..nn.layers import WNConvTranspose1d
from ..nn.quantize import ResidualVectorQuantize


def init_weights(m):
    if isinstance(m, nn.Conv1d):
        nn.init.trunc_normal_(m.weight, std=0.02)
        nn.init.constant_(m.bias, 0)


class ResidualUnit(nn.Module):
    def __init__(self, dim: int = 16, dilation: int = 1):
        super().__init__()
        pad = ((7 - 1) * dilation) // 2
        self.block = nn.Sequential(
            Snake1d(dim),
            WNConv1d(dim, dim, kernel_size=7, dilation=dilation, padding=pad),
            Snake1d(dim),
            WNConv1d(dim, dim, kernel_size=1),
        )

    def forward(self, x):
        y = self.block(x)
        pad = (x.shape[-1] - y.shape[-1]) // 2
        if pad > 0:
            x = x[..., pad:-pad]
        return x + y


class EncoderBlock(nn.Module):
    def __init__(self, dim: int = 16, stride: int = 1):
        super().__init__()
        self.block = nn.Sequential(
            ResidualUnit(dim // 2, dilation=1),
            ResidualUnit(dim // 2, dilation=3),
            ResidualUnit(dim // 2, dilation=9),
            Snake1d(dim // 2),
            WNConv1d(
                dim // 2,
                dim,
                kernel_size=2 * stride,
                stride=stride,
                padding=math.ceil(stride / 2),
            ),
        )

    def forward(self, x):
        return self.block(x)


class Encoder(nn.Module):
    def __init__(
        self,
        d_model: int = 64,
        strides: list = [2, 4, 8, 8],
        d_latent: int = 64,
    ):
        super().__init__()
        # Create first convolution
        self.block = [WNConv1d(1, d_model, kernel_size=7, padding=3)]

        # Create EncoderBlocks that double channels as they downsample by `stride`
        for stride in strides:
            d_model *= 2
            self.block += [EncoderBlock(d_model, stride=stride)]

        # Create last convolution
        self.block += [
            Snake1d(d_model),
            WNConv1d(d_model, d_latent, kernel_size=3, padding=1),
        ]

        # Wrap black into nn.Sequential
        self.block = nn.Sequential(*self.block)
        self.enc_dim = d_model

    def forward(self, x):
        return self.block(x)


class DecoderBlock(nn.Module):
    def __init__(self, input_dim: int = 16, output_dim: int = 8, stride: int = 1):
        super().__init__()
        self.block = nn.Sequential(
            Snake1d(input_dim),
            WNConvTranspose1d(
                input_dim,
                output_dim,
                kernel_size=2 * stride,
                stride=stride,
                padding=math.ceil(stride / 2),
            ),
            ResidualUnit(output_dim, dilation=1),
            ResidualUnit(output_dim, dilation=3),
            ResidualUnit(output_dim, dilation=9),
        )

    def forward(self, x):
        return self.block(x)


class Decoder(nn.Module):
    def __init__(
        self,
        input_channel,
        channels,
        rates,
        d_out: int = 1,
    ):
        super().__init__()

        # Add first conv layer
        layers = [WNConv1d(input_channel, channels, kernel_size=7, padding=3)]

        # Add upsampling + MRF blocks
        for i, stride in enumerate(rates):
            input_dim = channels // 2**i
            output_dim = channels // 2 ** (i + 1)
            layers += [DecoderBlock(input_dim, output_dim, stride)]

        # Add final conv layer
        layers += [
            Snake1d(output_dim),
            WNConv1d(output_dim, d_out, kernel_size=7, padding=3),
            nn.Tanh(),
        ]

        self.model = nn.Sequential(*layers)

    def forward(self, x):
        return self.model(x)


class DAC(BaseModel, CodecMixin):
    def __init__(
        self,
        encoder_dim: int = 64,
        encoder_rates: List[int] = [2, 4, 8, 8],
        latent_dim: int = None,
        decoder_dim: int = 1536,
        decoder_rates: List[int] = [8, 8, 4, 2],
        n_codebooks: int = 9,
        codebook_size: int = 1024,
        codebook_dim: Union[int, list] = 8,
        quantizer_dropout: bool = False,
        sample_rate: int = 44100,
    ):
        super().__init__()

        self.encoder_dim = encoder_dim
        self.encoder_rates = encoder_rates
        self.decoder_dim = decoder_dim
        self.decoder_rates = decoder_rates
        self.sample_rate = sample_rate

        if latent_dim is None:
            latent_dim = encoder_dim * (2 ** len(encoder_rates))

        self.latent_dim = latent_dim

        self.hop_length = np.prod(encoder_rates)
        self.encoder = Encoder(encoder_dim, encoder_rates, latent_dim)

        self.n_codebooks = n_codebooks
        self.codebook_size = codebook_size
        self.codebook_dim = codebook_dim
        self.quantizer = ResidualVectorQuantize(
            input_dim=latent_dim,
            n_codebooks=n_codebooks,
            codebook_size=codebook_size,
            codebook_dim=codebook_dim,
            quantizer_dropout=quantizer_dropout,
        )

        self.decoder = Decoder(
            latent_dim,
            decoder_dim,
            decoder_rates,
        )
        self.sample_rate = sample_rate
        self.apply(init_weights)

        self.delay = self.get_delay()

    def preprocess(self, audio_data, sample_rate):
        if sample_rate is None:
            sample_rate = self.sample_rate
        assert sample_rate == self.sample_rate

        length = audio_data.shape[-1]
        right_pad = math.ceil(length / self.hop_length) * self.hop_length - length
        audio_data = nn.functional.pad(audio_data, (0, right_pad))

        return audio_data

    def encode(
        self,
        audio_data: torch.Tensor,
        n_quantizers: int = None,
    ):
        """Encode given audio data and return quantized latent codes

        Parameters
        ----------
        audio_data : Tensor[B x 1 x T]
            Audio data to encode
        n_quantizers : int, optional
            Number of quantizers to use, by default None
            If None, all quantizers are used.

        Returns
        -------
        dict
            A dictionary with the following keys:
            "z" : Tensor[B x D x T]
                Quantized continuous representation of input
            "codes" : Tensor[B x N x T]
                Codebook indices for each codebook
                (quantized discrete representation of input)
            "latents" : Tensor[B x N*D x T]
                Projected latents (continuous representation of input before quantization)
            "vq/commitment_loss" : Tensor[1]
                Commitment loss to train encoder to predict vectors closer to codebook
                entries
            "vq/codebook_loss" : Tensor[1]
                Codebook loss to update the codebook
            "length" : int
                Number of samples in input audio
        """
        z = self.encoder(audio_data)
        z, codes, latents, commitment_loss, codebook_loss = self.quantizer(
            z, n_quantizers
        )
        return z, codes, latents, commitment_loss, codebook_loss

    def decode(self, z: torch.Tensor):
        """Decode given latent codes and return audio data

        Parameters
        ----------
        z : Tensor[B x D x T]
            Quantized continuous representation of input
        length : int, optional
            Number of samples in output audio, by default None

        Returns
        -------
        dict
            A dictionary with the following keys:
            "audio" : Tensor[B x 1 x length]
                Decoded audio data.
        """
        return self.decoder(z)

    def forward(
        self,
        audio_data: torch.Tensor,
        sample_rate: int = None,
        n_quantizers: int = None,
    ):
        """Model forward pass

        Parameters
        ----------
        audio_data : Tensor[B x 1 x T]
            Audio data to encode
        sample_rate : int, optional
            Sample rate of audio data in Hz, by default None
            If None, defaults to `self.sample_rate`
        n_quantizers : int, optional
            Number of quantizers to use, by default None.
            If None, all quantizers are used.

        Returns
        -------
        dict
            A dictionary with the following keys:
            "z" : Tensor[B x D x T]
                Quantized continuous representation of input
            "codes" : Tensor[B x N x T]
                Codebook indices for each codebook
                (quantized discrete representation of input)
            "latents" : Tensor[B x N*D x T]
                Projected latents (continuous representation of input before quantization)
            "vq/commitment_loss" : Tensor[1]
                Commitment loss to train encoder to predict vectors closer to codebook
                entries
            "vq/codebook_loss" : Tensor[1]
                Codebook loss to update the codebook
            "length" : int
                Number of samples in input audio
            "audio" : Tensor[B x 1 x length]
                Decoded audio data.
        """
        length = audio_data.shape[-1]
        audio_data = self.preprocess(audio_data, sample_rate)
        z, codes, latents, commitment_loss, codebook_loss = self.encode(
            audio_data, n_quantizers
        )

        x = self.decode(z)
        return {
            "audio": x[..., :length],
            "z": z,
            "codes": codes,
            "latents": latents,
            "vq/commitment_loss": commitment_loss,
            "vq/codebook_loss": codebook_loss,
        }


if __name__ == "__main__":
    import numpy as np
    from functools import partial

    model = DAC().to("cpu")

    for n, m in model.named_modules():
        o = m.extra_repr()
        p = sum([np.prod(p.size()) for p in m.parameters()])
        fn = lambda o, p: o + f" {p/1e6:<.3f}M params."
        setattr(m, "extra_repr", partial(fn, o=o, p=p))
    print(model)
    print("Total # of params: ", sum([np.prod(p.size()) for p in model.parameters()]))

    length = 88200 * 2
    x = torch.randn(1, 1, length).to(model.device)
    x.requires_grad_(True)
    x.retain_grad()

    # Make a forward pass
    out = model(x)["audio"]
    print("Input shape:", x.shape)
    print("Output shape:", out.shape)

    # Create gradient variable
    grad = torch.zeros_like(out)
    grad[:, :, grad.shape[-1] // 2] = 1

    # Make a backward pass
    out.backward(grad)

    # Check non-zero values
    gradmap = x.grad.squeeze(0)
    gradmap = (gradmap != 0).sum(0)  # sum across features
    rf = (gradmap != 0).sum()

    print(f"Receptive field: {rf.item()}")

    x = AudioSignal(torch.randn(1, 1, 44100 * 60), 44100)
    model.decompress(model.compress(x, verbose=True), verbose=True)