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": [
    "Wav2Vec2ForEmotionClassification"
  ],
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "configuration.Wav2Vec2ForEmotionClassificationConfig",
    "AutoModelForAudioClassification": "litagin/anime_speech_emotion_classification--modeling.Wav2Vec2ForEmotionClassification"
  },
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "codevector_dim": 768,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": true,
  "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": true,
  "eos_token_id": 2,
  "feat_extract_activation": "gelu",
  "feat_extract_dropout": 0.0,
  "feat_extract_norm": "layer",
  "feat_proj_dropout": 0.1,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.1,
  "finetuning_task": "wav2vec2_reg",
  "gradient_checkpointing": false,
  "head_activation": "relu",
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "Angry",
    "1": "Disgusted",
    "2": "Embarrassed",
    "3": "Fearful",
    "4": "Happy",
    "5": "Sad",
    "6": "Surprised",
    "7": "Neutral",
    "8": "Sexual1",
    "9": "Sexual2"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "Angry": 0,
    "Disgusted": 1,
    "Embarrassed": 2,
    "Fearful": 3,
    "Happy": 4,
    "Neutral": 7,
    "Sad": 5,
    "Sexual1": 8,
    "Sexual2": 9,
    "Surprised": 6
  },
  "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_for_emotion_classification",
  "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": 12,
  "num_negatives": 100,
  "output_hidden_size": 1024,
  "pad_token_id": 0,
  "pooling_mode": "mean",
  "problem_type": "regression",
  "proj_codevector_dim": 768,
  "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": "4.50.3",
  "use_weighted_layer_sum": false,
  "vocab_size": null,
  "xvector_output_dim": 512
}