config.json

{
  "_name_or_path": "openai/whisper-small",
  "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": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 50258,
  "dropout": 0.0,
  "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": 0,
    "1": 1,
    "10": 10,
    "11": 11,
    "12": 12,
    "13": 13,
    "14": 14,
    "15": 15,
    "16": 16,
    "17": 17,
    "18": 18,
    "19": 19,
    "2": 2,
    "20": 20,
    "21": 21,
    "22": 22,
    "23": 23,
    "24": 24,
    "25": 25,
    "26": 26,
    "27": 27,
    "28": 28,
    "29": 29,
    "3": 3,
    "30": 30,
    "31": 31,
    "32": 32,
    "33": 33,
    "34": 34,
    "35": 35,
    "4": 4,
    "5": 5,
    "6": 6,
    "7": 7,
    "8": 8,
    "9": 9
  },
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "label2id": {
    "0": 0,
    "1": 1,
    "10": 10,
    "11": 11,
    "12": 12,
    "13": 13,
    "14": 14,
    "15": 15,
    "16": 16,
    "17": 17,
    "18": 18,
    "19": 19,
    "2": 2,
    "20": 20,
    "21": 21,
    "22": 22,
    "23": 23,
    "24": 24,
    "25": 25,
    "26": 26,
    "27": 27,
    "28": 28,
    "29": 29,
    "3": 3,
    "30": 30,
    "31": 31,
    "32": 32,
    "33": 33,
    "34": 34,
    "35": 35,
    "4": 4,
    "5": 5,
    "6": 6,
    "7": 7,
    "8": 8,
    "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_length": 448,
  "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,
  "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,
    50360,
    50361,
    50362
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.35.0",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}