config.json

{
  "_name_or_path": "./model-results/cmd-turev/",
  "activation_dropout": 0.0,
  "apply_spec_augment": true,
  "architectures": [
    "HubertForSpeechClassification"
  ],
  "attention_dropout": 0.1,
  "bos_token_id": 1,
  "classifier_proj_size": 256,
  "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,
  "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_proj_layer_norm": true,
  "final_dropout": 0.0,
  "finetuning_task": "wav2vec2_clf",
  "gradient_checkpointing": false,
  "hidden_act": "gelu",
  "hidden_dropout": 0.1,
  "hidden_size": 1024,
  "id2label": {
    "0": "Angry",
    "1": "Calm",
    "2": "Happy",
    "3": "Sad"
  },
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "label2id": {
    "Angry": 0,
    "Calm": 1,
    "Happy": 2,
    "Sad": 3
  },
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "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": 0.075,
  "mask_time_selection": "static",
  "model_type": "hubert",
  "num_attention_heads": 16,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 24,
  "pad_token_id": 0,
  "pooling_mode": "mean",
  "problem_type": "single_label_classification",
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "torch_dtype": "float32",
  "transformers_version": "4.41.0.dev0",
  "use_weighted_layer_sum": false,
  "vocab_size": 32
}