# ################################
# Model: Pretrained SepFormer for source separation
# Dataset : Libri3Mix
# ################################

# Experiment params

sample_rate: 8000
num_spks: 3

# Encoder parameters
N_encoder_out: 256
out_channels: 256
kernel_size: 16
kernel_stride: 8

# Specifying the network
Encoder: &id003 !new:speechbrain.lobes.models.dual_path.Encoder
  kernel_size: 16
  out_channels: 256

SBtfintra: &id001 !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: &id002 !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: &id005 !new:speechbrain.lobes.models.dual_path.Dual_Path_Model
  num_spks: 3
  in_channels: 256
  out_channels: 256
  num_layers: 2
  K: 250
  intra_model: *id001
  inter_model: *id002
  norm: ln
  linear_layer_after_inter_intra: false
  skip_around_intra: true

Decoder: &id004 !new:speechbrain.lobes.models.dual_path.Decoder
  in_channels: 256
  out_channels: 1
  kernel_size: 16
  stride: 8
  bias: false

modules:
  encoder: *id003
  decoder: *id004
  masknet: *id005
  
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
  loadables:
     encoder: !ref <Encoder>
     masknet: !ref <MaskNet>
     decoder: !ref <Decoder>