{
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperForAudioClassification"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50256
  ],
  "bos_token_id": 50257,
  "classifier_proj_size": 512,
  "d_model": 256,
  "decoder_attention_heads": 4,
  "decoder_ffn_dim": 1536,
  "decoder_layer": 8,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_start_token_id": 50257,
  "dropout": 0.2,
  "encoder_attention_heads": 4,
  "encoder_ffn_dim": 1536,
  "encoder_layer": 8,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 6,
  "eos_token_id": 50256,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7",
    "8": "LABEL_8",
    "9": "LABEL_9",
    "10": "LABEL_10",
    "11": "LABEL_11",
    "12": "LABEL_12",
    "13": "LABEL_13",
    "14": "LABEL_14",
    "15": "LABEL_15",
    "16": "LABEL_16",
    "17": "LABEL_17",
    "18": "LABEL_18",
    "19": "LABEL_19",
    "20": "LABEL_20",
    "21": "LABEL_21",
    "22": "LABEL_22",
    "23": "LABEL_23",
    "24": "LABEL_24",
    "25": "LABEL_25",
    "26": "LABEL_26",
    "27": "LABEL_27",
    "28": "LABEL_28",
    "29": "LABEL_29",
    "30": "LABEL_30"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_10": 10,
    "LABEL_11": 11,
    "LABEL_12": 12,
    "LABEL_13": 13,
    "LABEL_14": 14,
    "LABEL_15": 15,
    "LABEL_16": 16,
    "LABEL_17": 17,
    "LABEL_18": 18,
    "LABEL_19": 19,
    "LABEL_2": 2,
    "LABEL_20": 20,
    "LABEL_21": 21,
    "LABEL_22": 22,
    "LABEL_23": 23,
    "LABEL_24": 24,
    "LABEL_25": 25,
    "LABEL_26": 26,
    "LABEL_27": 27,
    "LABEL_28": 28,
    "LABEL_29": 29,
    "LABEL_3": 3,
    "LABEL_30": 30,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "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": 50,
  "max_target_positions": 448,
  "model_type": "whisper",
  "num_hidden_layers": 6,
  "num_mel_bins": 80,
  "pad_token_id": 50256,
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.27.2",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 30
}