config.json

{
  "activation_dropout": 0.0,
  "adapter_attn_dim": null,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForMultiHeadMultiLabelClassification"
  ],
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_wav2vec2multihead.Wav2Vec2MultiHeadConfig",
    "AutoModelForAudioClassification": "modeling_wav2vec2multihead.Wav2Vec2ForMultiHeadMultiLabelClassification"
  },
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 256,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "ctc_loss_reduction": "sum",
  "ctc_zero_infinity": false,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": false,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.1,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.0,
  "freeze_feat_extract_train": true,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 768,
  "id2label": {
    "0": "activate",
    "1": "bring",
    "2": "change language",
    "3": "deactivate",
    "4": "decrease",
    "5": "increase",
    "6": "Chinese",
    "7": "English",
    "8": "German",
    "9": "Korean",
    "10": "heat",
    "11": "juice",
    "12": "lamp",
    "13": "lights",
    "14": "music",
    "15": "newspaper",
    "16": "none_object",
    "17": "shoes",
    "18": "socks",
    "19": "volume",
    "20": "bedroom",
    "21": "kitchen",
    "22": "none_location",
    "23": "washroom"
  },
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Chinese": 6,
    "English": 7,
    "German": 8,
    "Korean": 9,
    "activate": 0,
    "bedroom": 20,
    "bring": 1,
    "change language": 2,
    "deactivate": 3,
    "decrease": 4,
    "heat": 10,
    "increase": 5,
    "juice": 11,
    "kitchen": 21,
    "lamp": 12,
    "lights": 13,
    "music": 14,
    "newspaper": 15,
    "none_location": 22,
    "none_object": 16,
    "shoes": 17,
    "socks": 18,
    "volume": 19,
    "washroom": 23
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.0,
  "mask_channel_length": 10,
  "mask_channel_min_space": 1,
  "mask_channel_other": 0.0,
  "mask_channel_prob": 0.0,
  "mask_channel_selection": "static",
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "mask_feature_prob": 0.0,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_time_min_space": 1,
  "mask_time_other": 0.0,
  "mask_time_prob": 0.05,
  "mask_time_selection": "static",
  "model_type": "wav2vec2multihead_3class",
  "no_mask_channel_overlap": false,
  "no_mask_time_overlap": false,
  "num_adapter_layers": 3,
  "num_attention_heads": 12,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 12,
  "num_labels_1": 6,
  "num_labels_2": 14,
  "num_labels_3": 4,
  "num_negatives": 100,
  "output_hidden_size": 768,
  "pad_token_id": 0,
  "proj_codevector_dim": 256,
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.53.0",
  "use_weighted_layer_sum": false,
  "vocab_size": 32,
  "xvector_output_dim": 512
}