# CNN14 pre-trained on VGGSound with supervised objective

# Feature parameters
n_mels: 80

# Pretrain folder (HuggingFace)
pretrained_path: Ubenwa/sb-cssl-vgg-sup

# 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:crytorch.models.components.pann.Cnn14
  mel_bins: 80
  emb_dim: 2048
  norm_type: bn


classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier
    input_size: 2048
    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