File size: 1,522 Bytes
b52dc53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# ################################
# Model: Inference for source separation with SepFormer
# https://arxiv.org/abs/2010.13154
# Generated from speechbrain/recipes/WSJ0Mix/separation/train/hparams/sepformer-whamr-16khz.yaml
# Dataset : Whamr-16kHz
# ###############################


# Parameters
sample_rate: 16000
num_spks: 2

# Specifying the network
Encoder: !new:speechbrain.lobes.models.dual_path.Encoder
  kernel_size: 16
  out_channels: 256

SBtfintra: !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
  num_layers: 8
  d_model: 256
  nhead: 8
  d_ffn: 1024
  dropout: 0
  use_positional_encoding: true
  norm_before: true

SBtfinter: !new:speechbrain.lobes.models.dual_path.SBTransformerBlock
  num_layers: 8
  d_model: 256
  nhead: 8
  d_ffn: 1024
  dropout: 0
  use_positional_encoding: true
  norm_before: true

MaskNet: !new:speechbrain.lobes.models.dual_path.Dual_Path_Model
  num_spks: !ref <num_spks>
  in_channels: 256
  out_channels: 256
  num_layers: 2
  K: 250
  intra_model: !ref <SBtfintra>
  inter_model: !ref <SBtfinter>
  norm: ln
  linear_layer_after_inter_intra: false
  skip_around_intra: true

Decoder: !new:speechbrain.lobes.models.dual_path.Decoder
  in_channels: 256
  out_channels: 1
  kernel_size: 16
  stride: 8
  bias: false

modules:
  encoder: !ref <Encoder>
  decoder: !ref <Decoder>
  masknet: !ref <MaskNet>

pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
  loadables:
    masknet: !ref <MaskNet>
    encoder: !ref <Encoder>
    decoder: !ref <Decoder>