hyperparams.yaml

pretrained_path: ChainYo/speaker-recognition-meetup

# Model parameters
n_mels: 23
sample_rate: 16000
n_classes: 2
emb_dim: 512

# Feature extraction
compute_features: !new:speechbrain.lobes.features.Fbank
    n_mels: !ref <n_mels>

# Mean and std normalization of the input features
mean_var_norm: !new:speechbrain.processing.features.InputNormalization
    norm_type: sentence
    std_norm: False

# To design a custom model, either just edit the simple CustomModel
# class that's listed here, or replace this `!new` call with a line
# pointing to a different file you've defined.
embedding_model: !new:custom_model.Xvector
    in_channels: !ref <n_mels>
    activation: !name:torch.nn.LeakyReLU
    tdnn_blocks: 5
    tdnn_channels: [512, 512, 512, 512, 1500]
    tdnn_kernel_sizes: [5, 3, 3, 1, 1]
    tdnn_dilations: [1, 2, 3, 1, 1]
    lin_neurons: !ref <emb_dim>

classifier: !new:custom_model.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>

label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder

# Objects in "modules" dict will have their parameters moved to the correct
# device, as well as having train()/eval() called on them by the Brain class.
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>
        label_encoder: !ref <label_encoder>
    paths:
        embedding_model: !ref <pretrained_path>/embedding_model.ckpt
        classifier: !ref <pretrained_path>/classifier.ckpt
        label_encoder: !ref <pretrained_path>/label_encoder.txt