File size: 13,257 Bytes
e976963
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import torch.nn as nn
import torch, numpy as np
import torch.nn.functional as F
from librosa.filters import mel


class BiGRU(nn.Module):
    def __init__(self, input_features, hidden_features, num_layers):
        super(BiGRU, self).__init__()
        self.gru = nn.GRU(
            input_features,
            hidden_features,
            num_layers=num_layers,
            batch_first=True,
            bidirectional=True,
        )

    def forward(self, x):
        return self.gru(x)[0]


class ConvBlockRes(nn.Module):
    def __init__(self, in_channels, out_channels, momentum=0.01):
        super(ConvBlockRes, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(
                in_channels=in_channels,
                out_channels=out_channels,
                kernel_size=(3, 3),
                stride=(1, 1),
                padding=(1, 1),
                bias=False,
            ),
            nn.BatchNorm2d(out_channels, momentum=momentum),
            nn.ReLU(),
            nn.Conv2d(
                in_channels=out_channels,
                out_channels=out_channels,
                kernel_size=(3, 3),
                stride=(1, 1),
                padding=(1, 1),
                bias=False,
            ),
            nn.BatchNorm2d(out_channels, momentum=momentum),
            nn.ReLU(),
        )
        if in_channels != out_channels:
            self.shortcut = nn.Conv2d(in_channels, out_channels, (1, 1))
            self.is_shortcut = True
        else:
            self.is_shortcut = False

    def forward(self, x):
        if self.is_shortcut:
            return self.conv(x) + self.shortcut(x)
        else:
            return self.conv(x) + x


class Encoder(nn.Module):
    def __init__(
        self,
        in_channels,
        in_size,
        n_encoders,
        kernel_size,
        n_blocks,
        out_channels=16,
        momentum=0.01,
    ):
        super(Encoder, self).__init__()
        self.n_encoders = n_encoders
        self.bn = nn.BatchNorm2d(in_channels, momentum=momentum)
        self.layers = nn.ModuleList()
        self.latent_channels = []
        for i in range(self.n_encoders):
            self.layers.append(
                ResEncoderBlock(
                    in_channels, out_channels, kernel_size, n_blocks, momentum=momentum
                )
            )
            self.latent_channels.append([out_channels, in_size])
            in_channels = out_channels
            out_channels *= 2
            in_size //= 2
        self.out_size = in_size
        self.out_channel = out_channels

    def forward(self, x):
        concat_tensors = []
        x = self.bn(x)
        for i in range(self.n_encoders):
            _, x = self.layers[i](x)
            concat_tensors.append(_)
        return x, concat_tensors


class ResEncoderBlock(nn.Module):
    def __init__(
        self, in_channels, out_channels, kernel_size, n_blocks=1, momentum=0.01
    ):
        super(ResEncoderBlock, self).__init__()
        self.n_blocks = n_blocks
        self.conv = nn.ModuleList()
        self.conv.append(ConvBlockRes(in_channels, out_channels, momentum))
        for i in range(n_blocks - 1):
            self.conv.append(ConvBlockRes(out_channels, out_channels, momentum))
        self.kernel_size = kernel_size
        if self.kernel_size is not None:
            self.pool = nn.AvgPool2d(kernel_size=kernel_size)

    def forward(self, x):
        for i in range(self.n_blocks):
            x = self.conv[i](x)
        if self.kernel_size is not None:
            return x, self.pool(x)
        else:
            return x


class Intermediate(nn.Module):  #
    def __init__(self, in_channels, out_channels, n_inters, n_blocks, momentum=0.01):
        super(Intermediate, self).__init__()
        self.n_inters = n_inters
        self.layers = nn.ModuleList()
        self.layers.append(
            ResEncoderBlock(in_channels, out_channels, None, n_blocks, momentum)
        )
        for i in range(self.n_inters - 1):
            self.layers.append(
                ResEncoderBlock(out_channels, out_channels, None, n_blocks, momentum)
            )

    def forward(self, x):
        for i in range(self.n_inters):
            x = self.layers[i](x)
        return x


class ResDecoderBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride, n_blocks=1, momentum=0.01):
        super(ResDecoderBlock, self).__init__()
        out_padding = (0, 1) if stride == (1, 2) else (1, 1)
        self.n_blocks = n_blocks
        self.conv1 = nn.Sequential(
            nn.ConvTranspose2d(
                in_channels=in_channels,
                out_channels=out_channels,
                kernel_size=(3, 3),
                stride=stride,
                padding=(1, 1),
                output_padding=out_padding,
                bias=False,
            ),
            nn.BatchNorm2d(out_channels, momentum=momentum),
            nn.ReLU(),
        )
        self.conv2 = nn.ModuleList()
        self.conv2.append(ConvBlockRes(out_channels * 2, out_channels, momentum))
        for i in range(n_blocks - 1):
            self.conv2.append(ConvBlockRes(out_channels, out_channels, momentum))

    def forward(self, x, concat_tensor):
        x = self.conv1(x)
        x = torch.cat((x, concat_tensor), dim=1)
        for i in range(self.n_blocks):
            x = self.conv2[i](x)
        return x


class Decoder(nn.Module):
    def __init__(self, in_channels, n_decoders, stride, n_blocks, momentum=0.01):
        super(Decoder, self).__init__()
        self.layers = nn.ModuleList()
        self.n_decoders = n_decoders
        for i in range(self.n_decoders):
            out_channels = in_channels // 2
            self.layers.append(
                ResDecoderBlock(in_channels, out_channels, stride, n_blocks, momentum)
            )
            in_channels = out_channels

    def forward(self, x, concat_tensors):
        for i in range(self.n_decoders):
            x = self.layers[i](x, concat_tensors[-1 - i])
        return x


class DeepUnet(nn.Module):
    def __init__(
        self,
        kernel_size,
        n_blocks,
        en_de_layers=5,
        inter_layers=4,
        in_channels=1,
        en_out_channels=16,
    ):
        super(DeepUnet, self).__init__()
        self.encoder = Encoder(
            in_channels, 128, en_de_layers, kernel_size, n_blocks, en_out_channels
        )
        self.intermediate = Intermediate(
            self.encoder.out_channel // 2,
            self.encoder.out_channel,
            inter_layers,
            n_blocks,
        )
        self.decoder = Decoder(
            self.encoder.out_channel, en_de_layers, kernel_size, n_blocks
        )

    def forward(self, x):
        x, concat_tensors = self.encoder(x)
        x = self.intermediate(x)
        x = self.decoder(x, concat_tensors)
        return x


class E2E(nn.Module):
    def __init__(
        self,
        n_blocks,
        n_gru,
        kernel_size,
        en_de_layers=5,
        inter_layers=4,
        in_channels=1,
        en_out_channels=16,
    ):
        super(E2E, self).__init__()
        self.unet = DeepUnet(
            kernel_size,
            n_blocks,
            en_de_layers,
            inter_layers,
            in_channels,
            en_out_channels,
        )
        self.cnn = nn.Conv2d(en_out_channels, 3, (3, 3), padding=(1, 1))
        if n_gru:
            self.fc = nn.Sequential(
                BiGRU(3 * 128, 256, n_gru),
                nn.Linear(512, 360),
                nn.Dropout(0.25),
                nn.Sigmoid(),
            )

    def forward(self, mel):
        mel = mel.transpose(-1, -2).unsqueeze(1)
        x = self.cnn(self.unet(mel)).transpose(1, 2).flatten(-2)
        x = self.fc(x)
        return x


class MelSpectrogram(torch.nn.Module):
    def __init__(
        self,
        is_half,
        n_mel_channels,
        sampling_rate,
        win_length,
        hop_length,
        n_fft=None,
        mel_fmin=0,
        mel_fmax=None,
        clamp=1e-5,
    ):
        super().__init__()
        n_fft = win_length if n_fft is None else n_fft
        self.hann_window = {}
        mel_basis = mel(
            sr=sampling_rate,
            n_fft=n_fft,
            n_mels=n_mel_channels,
            fmin=mel_fmin,
            fmax=mel_fmax,
            htk=True,
        )
        mel_basis = torch.from_numpy(mel_basis).float()
        self.register_buffer("mel_basis", mel_basis)
        self.n_fft = win_length if n_fft is None else n_fft
        self.hop_length = hop_length
        self.win_length = win_length
        self.sampling_rate = sampling_rate
        self.n_mel_channels = n_mel_channels
        self.clamp = clamp
        self.is_half = is_half

    def forward(self, audio, keyshift=0, speed=1, center=True):
        factor = 2 ** (keyshift / 12)
        n_fft_new = int(np.round(self.n_fft * factor))
        win_length_new = int(np.round(self.win_length * factor))
        hop_length_new = int(np.round(self.hop_length * speed))
        keyshift_key = str(keyshift) + "_" + str(audio.device)
        if keyshift_key not in self.hann_window:
            self.hann_window[keyshift_key] = torch.hann_window(win_length_new).to(
                audio.device
            )
        fft = torch.stft(
            audio,
            n_fft=n_fft_new,
            hop_length=hop_length_new,
            win_length=win_length_new,
            window=self.hann_window[keyshift_key],
            center=center,
            return_complex=True,
        )
        magnitude = torch.sqrt(fft.real.pow(2) + fft.imag.pow(2))
        if keyshift != 0:
            size = self.n_fft // 2 + 1
            resize = magnitude.size(1)
            if resize < size:
                magnitude = F.pad(magnitude, (0, 0, 0, size - resize))
            magnitude = magnitude[:, :size, :] * self.win_length / win_length_new
        mel_output = torch.matmul(self.mel_basis, magnitude)
        if self.is_half == True:
            mel_output = mel_output.half()
        log_mel_spec = torch.log(torch.clamp(mel_output, min=self.clamp))
        return log_mel_spec


class RMVPE:
    def __init__(self, model_path, is_half, device=None):
        self.resample_kernel = {}
        model = E2E(4, 1, (2, 2))
        ckpt = torch.load(model_path, map_location="cpu")
        model.load_state_dict(ckpt)
        model.eval()
        if is_half == True:
            model = model.half()
        self.model = model
        self.resample_kernel = {}
        self.is_half = is_half
        if device is None:
            device = "cuda" if torch.cuda.is_available() else "cpu"
        self.device = device
        self.mel_extractor = MelSpectrogram(
            is_half, 128, 16000, 1024, 160, None, 30, 8000
        ).to(device)
        self.model = self.model.to(device)
        cents_mapping = 20 * np.arange(360) + 1997.3794084376191
        self.cents_mapping = np.pad(cents_mapping, (4, 4))  # 368

    def mel2hidden(self, mel):
        with torch.no_grad():
            n_frames = mel.shape[-1]
            mel = F.pad(
                mel, (0, 32 * ((n_frames - 1) // 32 + 1) - n_frames), mode="reflect"
            )
            hidden = self.model(mel)
            return hidden[:, :n_frames]

    def decode(self, hidden, thred=0.03):
        cents_pred = self.to_local_average_cents(hidden, thred=thred)
        f0 = 10 * (2 ** (cents_pred / 1200))
        f0[f0 == 10] = 0
        return f0

    def infer_from_audio(self, audio, thred=0.03):
        audio = torch.from_numpy(audio).float().to(self.device).unsqueeze(0)
        mel = self.mel_extractor(audio, center=True)
        hidden = self.mel2hidden(mel)
        hidden = hidden.squeeze(0).cpu().numpy()
        if self.is_half == True:
            hidden = hidden.astype("float32")
        f0 = self.decode(hidden, thred=thred)
        return f0

    def to_local_average_cents(self, salience, thred=0.05):
        center = np.argmax(salience, axis=1)
        salience = np.pad(salience, ((0, 0), (4, 4)))
        center += 4
        todo_salience = []
        todo_cents_mapping = []
        starts = center - 4
        ends = center + 5
        for idx in range(salience.shape[0]):
            todo_salience.append(salience[:, starts[idx] : ends[idx]][idx])
            todo_cents_mapping.append(self.cents_mapping[starts[idx] : ends[idx]])
        todo_salience = np.array(todo_salience)
        todo_cents_mapping = np.array(todo_cents_mapping)
        product_sum = np.sum(todo_salience * todo_cents_mapping, 1)
        weight_sum = np.sum(todo_salience, 1)
        devided = product_sum / weight_sum
        maxx = np.max(salience, axis=1)
        devided[maxx <= thred] = 0
        return devided

    def infer_from_audio_with_pitch(self, audio, thred=0.03, f0_min=50, f0_max=1100):
        audio = torch.from_numpy(audio).float().to(self.device).unsqueeze(0)
        mel = self.mel_extractor(audio, center=True)
        hidden = self.mel2hidden(mel)
        hidden = hidden.squeeze(0).cpu().numpy()
        if self.is_half == True:
            hidden = hidden.astype("float32")
        f0 = self.decode(hidden, thred=thred)
        f0[(f0 < f0_min) | (f0 > f0_max)] = 0  
        return f0