|
|
|
sample_rate: 16000
|
|
n_mels: 40
|
|
|
|
|
|
emb_dim: 128
|
|
n_classes: 5
|
|
tdnn_channels: 64
|
|
tdnn_channels_out: 128
|
|
|
|
label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
|
|
|
|
|
|
|
|
compute_features: !new:speechbrain.lobes.features.Fbank
|
|
n_mels: !ref <n_mels>
|
|
|
|
mean_var_norm: !new:speechbrain.processing.features.InputNormalization
|
|
norm_type: sentence
|
|
std_norm: False
|
|
|
|
embedding_model: !new:speechbrain.lobes.models.Xvector.Xvector
|
|
in_channels: !ref <n_mels>
|
|
tdnn_blocks: 5
|
|
tdnn_channels:
|
|
- !ref <tdnn_channels>
|
|
- !ref <tdnn_channels>
|
|
- !ref <tdnn_channels>
|
|
- !ref <tdnn_channels>
|
|
- !ref <tdnn_channels_out>
|
|
tdnn_kernel_sizes: [5, 3, 3, 1, 1]
|
|
tdnn_dilations: [1, 2, 3, 1, 1]
|
|
lin_neurons: !ref <emb_dim>
|
|
|
|
classifier: !new:speechbrain.lobes.models.Xvector.Classifier
|
|
input_shape: [null, null, !ref <emb_dim>]
|
|
activation: !name:torch.nn.LeakyReLU
|
|
lin_blocks: 1
|
|
lin_neurons: !ref <emb_dim>
|
|
out_neurons: !ref <n_classes>
|
|
|
|
modules:
|
|
compute_features: !ref <compute_features>
|
|
embedding_model: !ref <embedding_model>
|
|
classifier: !ref <classifier>
|
|
mean_var_norm: !ref <mean_var_norm>
|
|
|
|
pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
|
|
loadables:
|
|
embedding_model: !ref <embedding_model>
|
|
classifier: !ref <classifier> |
