| |
|
|
| |
| n_mels: 80 |
|
|
| |
| pretrained_path: Ubenwa/sb-cssl-vgg-sclr |
|
|
| |
| out_n_neurons: 308 |
|
|
| |
| 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 |
|
|
| classifier: !new:speechbrain.lobes.models.ECAPA_TDNN.Classifier |
| input_size: 2048 |
| out_neurons: !ref <out_n_neurons> |
|
|
| embedding_model: !new:speechbrain.nnet.containers.LengthsCapableSequential |
| input_shape: [null, 1, null] |
| embedding: !new:crytorch.models.components.pann.Cnn14 |
| mel_bins: 80 |
| emb_dim: 2048 |
| norm_type: bn |
| projector: !new:crytorch.models.components.pann.SimSiamProjector |
| input_size: 2048 |
| hidden_size: 2048 |
| output_size: 2048 |
| norm_type: bn |
|
|
| 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 |
|
|
|
|
|
|
