{
  "_name_or_path": "openai/whisper-base",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperForAudioClassification"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50257
  ],
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 512,
  "decoder_attention_heads": 8,
  "decoder_ffn_dim": 2048,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "encoder_attention_heads": 8,
  "encoder_ffn_dim": 2048,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 6,
  "eos_token_id": 50257,
  "finetuning_task": "audio-classification",
  "forced_decoder_ids": [
    [
      1,
      50259
    ],
    [
      2,
      50359
    ],
    [
      3,
      50363
    ]
  ],
  "id2label": {
    "0": "alif",
    "1": "seen",
    "10": "wao",
    "11": "kaif",
    "12": "duad",
    "13": "faa",
    "14": "tua",
    "15": "suad",
    "16": "ba",
    "17": "noon",
    "18": "yaa",
    "19": "hha",
    "2": "zua",
    "20": "hamzah",
    "21": "sheen",
    "22": "meem",
    "23": "quaf",
    "24": "zhal",
    "25": "sa",
    "26": "jeem",
    "27": "aain",
    "28": "zaa",
    "3": "ta",
    "4": "kha",
    "5": "dal",
    "6": "haa",
    "7": "laam",
    "8": "raa",
    "9": "ghain"
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "aain": "27",
    "alif": "0",
    "ba": "16",
    "dal": "5",
    "duad": "12",
    "faa": "13",
    "ghain": "9",
    "haa": "6",
    "hamzah": "20",
    "hha": "19",
    "jeem": "26",
    "kaif": "11",
    "kha": "4",
    "laam": "7",
    "meem": "22",
    "noon": "17",
    "quaf": "23",
    "raa": "8",
    "sa": "25",
    "seen": "1",
    "sheen": "21",
    "suad": "15",
    "ta": "3",
    "tua": "14",
    "wao": "10",
    "yaa": "18",
    "zaa": "28",
    "zhal": "24",
    "zua": "2"
  },
  "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_length": 448,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 6,
  "num_mel_bins": 80,
  "pad_token_id": 50257,
  "scale_embedding": false,
  "suppress_tokens": [
    1,
    2,
    7,
    8,
    9,
    10,
    14,
    25,
    26,
    27,
    28,
    29,
    31,
    58,
    59,
    60,
    61,
    62,
    63,
    90,
    91,
    92,
    93,
    359,
    503,
    522,
    542,
    873,
    893,
    902,
    918,
    922,
    931,
    1350,
    1853,
    1982,
    2460,
    2627,
    3246,
    3253,
    3268,
    3536,
    3846,
    3961,
    4183,
    4667,
    6585,
    6647,
    7273,
    9061,
    9383,
    10428,
    10929,
    11938,
    12033,
    12331,
    12562,
    13793,
    14157,
    14635,
    15265,
    15618,
    16553,
    16604,
    18362,
    18956,
    20075,
    21675,
    22520,
    26130,
    26161,
    26435,
    28279,
    29464,
    31650,
    32302,
    32470,
    36865,
    42863,
    47425,
    49870,
    50254,
    50258,
    50358,
    50359,
    50360,
    50361,
    50362
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.36.0.dev0",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}