config.json

{
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperForAudioClassification"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "dtype": "float32",
  "encoder_attention_heads": 12,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 50257,
  "forced_decoder_ids": [
    [
      1,
      50259
    ],
    [
      2,
      50359
    ],
    [
      3,
      50363
    ]
  ],
  "id2label": {
    "0": "angry",
    "1": "calm",
    "2": "disgust",
    "3": "fearful",
    "4": "happy",
    "5": "neutral",
    "6": "sad",
    "7": "surprised"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "angry": 0,
    "calm": 1,
    "disgust": 2,
    "fearful": 3,
    "happy": 4,
    "neutral": 5,
    "sad": 6,
    "surprised": 7
  },
  "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,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 12,
  "num_mel_bins": 80,
  "pad_token_id": 50257,
  "scale_embedding": false,
  "tie_word_embeddings": true,
  "transformers_version": "5.0.0",
  "use_cache": false,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}