{
  "architectures": [
    "XvectorModel"
  ],
  "auto_map": {
    "AutoConfig": "configuration_xvector.XvectorConfig",
    "AutoModel": "modeling_xvector.XvectorModel",
    "AutoModelForAudioClassification": "modeling_xvector.XvectorModelForSequenceClassification"
  },
  "hidden_size": 512,
  "hop_length": 10,
  "initializer_range": 0.02,
  "loss_fn": "aam",
  "mean_norm": true,
  "model_type": "xvector",
  "n_mels": 40,
  "norm_type": "sentence",
  "num_classes": 5994,
  "sample_rate": 16000,
  "std_norm": false,
  "tdnn_blocks": 5,
  "tdnn_channels": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_dilations": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_kernel_sizes": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.31.0",
  "win_length": 25
}