LightSpeech/model.txt at master · rishikksh20/LightSpeech · GitHub

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
FeedForwardTransformer(
  (encoder): Encoder(
    (after_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
    (embed): Sequential(
      (0): Embedding(87, 256, padding_idx=0)
      (1): ScaledPositionalEncoding(
        (dropout): Dropout(p=0.2, inplace=False)
      )
    )
    (encoders_): ModuleList(
      (0): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(5,), stride=(1,), padding=(2,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (1): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(25,), stride=(1,), padding=(12,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (2): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(13,), stride=(1,), padding=(6,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (3): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(9,), stride=(1,), padding=(4,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
    )
  )
  (duration_predictor): DurationPredictor(
    (conv): ModuleList(
      (0): Sequential(
        (0): SepConv1d(
          (depthwise): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,), groups=256)
          (pointwise): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
        )
        (1): ReLU()
        (2): LayerNorm(
          (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True)
        )
        (3): Dropout(p=0.5, inplace=False)
      )
      (1): Sequential(
        (0): SepConv1d(
          (depthwise): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,), groups=256)
          (pointwise): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
        )
        (1): ReLU()
        (2): LayerNorm(
          (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True)
        )
        (3): Dropout(p=0.5, inplace=False)
      )
    )
    (linear): Linear(in_features=256, out_features=1, bias=True)
  )
  (energy_predictor): EnergyPredictor(
    (predictor): VariancePredictor(
      (conv): ModuleList(
        (0): Sequential(
          (0): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,), groups=256)
            (pointwise): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
          )
          (1): ReLU()
          (2): LayerNorm(
            (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True)
          )
          (3): Dropout(p=0.5, inplace=False)
        )
        (1): Sequential(
          (0): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,), groups=256)
            (pointwise): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
          )
          (1): ReLU()
          (2): LayerNorm(
            (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True)
          )
          (3): Dropout(p=0.5, inplace=False)
        )
      )
      (linear): Linear(in_features=256, out_features=1, bias=True)
    )
  )
  (energy_embed): Linear(in_features=256, out_features=256, bias=True)
  (pitch_predictor): PitchPredictor(
    (predictor): VariancePredictor(
      (conv): ModuleList(
        (0): Sequential(
          (0): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,), groups=256)
            (pointwise): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
          )
          (1): ReLU()
          (2): LayerNorm(
            (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True)
          )
          (3): Dropout(p=0.5, inplace=False)
        )
        (1): Sequential(
          (0): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(3,), stride=(1,), padding=(1,), groups=256)
            (pointwise): Conv1d(256, 256, kernel_size=(1,), stride=(1,))
          )
          (1): ReLU()
          (2): LayerNorm(
            (layer_norm): LayerNorm((256,), eps=1e-12, elementwise_affine=True)
          )
          (3): Dropout(p=0.5, inplace=False)
        )
      )
      (linear): Linear(in_features=256, out_features=1, bias=True)
    )
  )
  (pitch_embed): Linear(in_features=256, out_features=256, bias=True)
  (length_regulator): LengthRegulator()
  (decoder): Encoder(
    (after_norm): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
    (embed): Sequential(
      (0): ScaledPositionalEncoding(
        (dropout): Dropout(p=0.2, inplace=False)
      )
    )
    (encoders_): ModuleList(
      (0): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(17,), stride=(1,), padding=(8,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (1): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(21,), stride=(1,), padding=(10,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (2): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(9,), stride=(1,), padding=(4,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
      (3): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linear_q): Linear(in_features=256, out_features=256, bias=True)
          (linear_k): Linear(in_features=256, out_features=256, bias=True)
          (linear_v): Linear(in_features=256, out_features=256, bias=True)
          (linear_out): Linear(in_features=256, out_features=256, bias=True)
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (feed_forward): MultiLayeredSepConv1d(
          (w_1): SepConv1d(
            (depthwise): Conv1d(256, 256, kernel_size=(13,), stride=(1,), padding=(6,), groups=256)
            (pointwise): Conv1d(256, 1024, kernel_size=(1,), stride=(1,))
          )
          (w_2): SepConv1d(
            (depthwise): Conv1d(1024, 1024, kernel_size=(1,), stride=(1,), groups=1024)
            (pointwise): Conv1d(1024, 256, kernel_size=(1,), stride=(1,))
          )
          (dropout): Dropout(p=0.2, inplace=False)
        )
        (norm1): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (norm2): LayerNorm((256,), eps=1e-05, elementwise_affine=True)
        (dropout): Dropout(p=0.2, inplace=False)
        (concat_linear): Linear(in_features=512, out_features=256, bias=True)
      )
    )
  )
  (feat_out): Linear(in_features=256, out_features=80, bias=True)
  (duration_criterion): DurationPredictorLoss(
    (criterion): MSELoss()
  )
  (energy_criterion): EnergyPredictorLoss(
    (criterion): MSELoss()
  )
  (pitch_criterion): PitchPredictorLoss(
    (criterion): MSELoss()
  )
  (criterion): L1Loss()
)