# ############################################################################
# Model: ECAPA pre-trained with SimCLR using VGGSound
# ############################################################################

# Feature parameters
n_mels: 80

# Pretrain folder (HuggingFace)
pretrained_path: gorinars/sb-ecapa-vggsound-simclr

# Output parameters
out_n_neurons: 308

# Model params
compute_features: !new:speechbrain.lobes.features.Fbank
  n_mels: 80
  left_frames: 0
  right_frames: 0
  deltas: false
  sample_rate: 16000
  n_fft: 400
  win_length: 25
  hop_length: 10
  f_min: 0


mean_var_norm: !new:speechbrain.processing.features.InputNormalization
    norm_type: sentence
    std_norm: False


embedding_model: !new:speechbrain.nnet.containers.LengthsCapableSequential
    input_shape: [null, 1, null]
    embedding: !new:speechbrain.lobes.models.ECAPA_TDNN.ECAPA_TDNN
        input_size: !ref <n_mels>
        channels: [1024, 1024, 1024, 1024, 3072]
        kernel_sizes: [5, 3, 3, 3, 1]
        dilations: [1, 2, 3, 4, 1]
        groups: [1, 1, 1, 1, 1]
        attention_channels: 128
        lin_neurons: 256
    projector: !new:crytorch.models.components.pann.SimSiamProjector
        input_size: 256
        hidden_size: 256
        output_size: 256
        norm_type: bn

        
classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
    input_size: 256
    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: !ref <embedding_model.embedding>
        projector: !ref <embedding_model.projector>
    paths:
        embedding: !ref <pretrained_path>/embedding_model.ckpt
        projector: !ref <pretrained_path>/projector.ckpt