| # ############################################################################ | |
| # Model: ECAPA VoxCeleb finetuned on CryCeleb to verify babies | |
| # ############################################################################ | |
| # Feature parameters | |
| n_mels: 80 | |
| # Pretrain folder (HuggingFace) | |
| pretrained_path: Ubenwa/ecapa-voxceleb-ft-cryceleb | |
| # 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, 3, 1] | |
| dilations: [1, 2, 3, 4, 1] | |
| attention_channels: 128 | |
| lin_neurons: 192 | |
| modules: | |
| compute_features: !ref <compute_features> | |
| mean_var_norm: !ref <mean_var_norm> | |
| embedding_model: !ref <embedding_model> | |
| pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer | |
| loadables: | |
| embedding_model: !ref <embedding_model> | |
| paths: | |
| embedding_model: !ref <pretrained_path>/embedding_model.ckpt | |