config.json

{
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "attention_dropout": 0.0,
  "bos_token_id": 50257,
  "d_model": 384,
  "decoder_attention_heads": 6,
  "decoder_ffn_dim": 1536,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 4,
  "decoder_start_token_id": 50257,
  "dropout": 0.0,
  "encoder_attention_heads": 6,
  "encoder_ffn_dim": 1536,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 4,
  "eos_token_id": 50257,
  "feature_size": 1,
  "init_std": 0.02,
  "input_channels": 1,
  "is_encoder_decoder": true,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "model_type": "whisper",
  "non_speech_tokens": [
    1,
    2,
    6,
    7,
    8,
    9,
    10,
    12,
    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
  ],
  "num_hidden_layers": 4,
  "num_mel_bins": 80,
  "pad_token_id": 0,
  "scale_embedding": false,
  "transformers_version": "4.23.0.dev0",
  "use_cache": true,
  "vocab_size": 51864
}