config.json

{
  "activation_dropout": 0.1,
  "adapter_attn_dim": null,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForSequenceClassification"
  ],
  "attention_dropout": 0.1,
  "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_dropout": 0.0,
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.0,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "admiring",
    "1": "affectionate",
    "2": "amused",
    "3": "angry",
    "4": "anxious",
    "5": "apologetic",
    "6": "betrayed",
    "7": "bittersweet",
    "8": "calming",
    "9": "casual",
    "10": "cheerful",
    "11": "cold",
    "12": "confiding",
    "13": "curious",
    "14": "disappointed-exasperated",
    "15": "dominant",
    "16": "grateful",
    "17": "horny",
    "18": "melancholic",
    "19": "problem-solving",
    "20": "reassuring",
    "21": "sarcastic",
    "22": "vulnerable"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "admiring": 0,
    "affectionate": 1,
    "amused": 2,
    "angry": 3,
    "anxious": 4,
    "apologetic": 5,
    "betrayed": 6,
    "bittersweet": 7,
    "calming": 8,
    "casual": 9,
    "cheerful": 10,
    "cold": 11,
    "confiding": 12,
    "curious": 13,
    "disappointed-exasperated": 14,
    "dominant": 15,
    "grateful": 16,
    "horny": 17,
    "melancholic": 18,
    "problem-solving": 19,
    "reassuring": 20,
    "sarcastic": 21,
    "vulnerable": 22
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "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_prob": 0.05,
  "model_type": "wav2vec2",
  "num_adapter_layers": 3,
  "num_attention_heads": 16,
  "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": 24,
  "num_negatives": 100,
  "output_hidden_size": 1024,
  "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": "4.52.4",
  "use_weighted_layer_sum": false,
  "vocab_size": 32,
  "xvector_output_dim": 512
}