REAL-M-sisnr-estimator / hyperparams.yaml
cemsubakan's picture
simplified hyperparams.yaml and adding hyperparams_train.yaml
ca690f1
raw
history blame
1.96 kB
# ################################
# Model: Neural SI-SNR Estimator with Pool training strategy (https://arxiv.org/pdf/2110.10812.pdf)
# Dataset : LibriMix and WHAMR!
# ################################
sample_rate: 8000
# Specifying the network
snrmin: 0
snrmax: 10
use_snr_compression: true
separation_norm_type: stnorm
latent_dim: 128
n_inp: 256
encoder: &id006 !new:speechbrain.nnet.containers.Sequential
input_shape: [!!null '', 2, !!null '']
cnn1: !new:speechbrain.nnet.CNN.Conv1d
in_channels: 2
kernel_size: 4
out_channels: 128
stride: 1
skip_transpose: true
padding: valid
relu1: !new:torch.nn.ReLU
cnn2: !new:speechbrain.nnet.CNN.Conv1d
in_channels: 128
kernel_size: 4
out_channels: 128
stride: 2
skip_transpose: true
padding: valid
relu2: !new:torch.nn.ReLU
cnn3: !new:speechbrain.nnet.CNN.Conv1d
in_channels: 128
kernel_size: 4
out_channels: 128
stride: 2
skip_transpose: true
padding: valid
relu3: !new:torch.nn.ReLU
cnn4: !new:speechbrain.nnet.CNN.Conv1d
in_channels: 128
kernel_size: 4
out_channels: 128
stride: 2
skip_transpose: true
padding: valid
relu4: !new:torch.nn.ReLU
cnn5: !new:speechbrain.nnet.CNN.Conv1d
in_channels: 128
kernel_size: 4
out_channels: 128
stride: 2
skip_transpose: true
padding: valid
stat_pooling: !new:speechbrain.nnet.pooling.StatisticsPooling
encoder_out: &id007 !new:speechbrain.nnet.containers.Sequential
input_shape: [!!null '', 256]
layer1: !new:speechbrain.nnet.linear.Linear
input_size: 256
n_neurons: 256
relu: !new:torch.nn.ReLU
layer2: !new:speechbrain.nnet.linear.Linear
input_size: 256
n_neurons: 1
sigm: !new:torch.nn.Sigmoid
modules:
encoder: *id006
encoder_out: *id007
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
loadables:
encoder: !ref <encoder>
encoder_out: !ref <encoder_out>