hyperparams.yaml

# ############################################################################
# Model: xvector for Sound Classification with UrbanSound8k
# ############################################################################

# Pretrain folder (HuggingFace)
pretrained_path: speechbrain/urbansound8k_ecapa 

# Feature parameters
n_mels: 80

# Output parameters
out_n_neurons: 10 # Possible sounds in the dataset


# Model params
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.ECAPA_TDNN.ECAPA_TDNN
    input_size: !ref <n_mels>
    channels: [1024, 1024, 1024, 1024, 3072]
    kernel_sizes: [5, 3, 3, 1, 1]
    dilations: [1, 2, 3, 4, 1]
    attention_channels: 128
    lin_neurons: 192

classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
    input_shape: 192
    out_neurons: !ref <out_n_neurons>

modules:
    compute_features: !ref <compute_features>
    mean_var_norm: !ref <mean_var_norm>
    embedding_model: !ref <embedding_model>
    classifier: !ref <classifier>

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

        
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