config.json

{
  "_name_or_path": "openai/whisper-small",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "adapter_attn_dim": null,
  "adapter_kernel_size": 3,
  "adapter_stride": 2,
  "add_adapter": false,
  "apply_spec_augment": true,
  "architectures": [
    "Wav2Vec2ForCTC"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50257
  ],
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "codevector_dim": 256,
  "contrastive_logits_temperature": 0.1,
  "conv_bias": false,
  "conv_dim": [
    512,
    512,
    512,
    512,
    512,
    512,
    512
  ],
  "conv_kernel": [
    10,
    3,
    3,
    3,
    3,
    2,
    2
  ],
  "conv_stride": [
    5,
    2,
    2,
    2,
    2,
    2,
    2
  ],
  "ctc_loss_reduction": "mean",
  "ctc_zero_infinity": false,
  "d_model": 768,
  "decoder_attention_heads": 12,
  "decoder_ffn_dim": 3072,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 12,
  "decoder_start_token_id": 50258,
  "diversity_loss_weight": 0.1,
  "do_stable_layer_norm": false,
  "dropout": 0.0,
  "encoder_attention_heads": 12,
  "encoder_ffn_dim": 3072,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 12,
  "eos_token_id": 50257,
  "feat_extract_activation": "gelu",
  "feat_extract_norm": "group",
  "feat_proj_dropout": 0.0,
  "feat_quantizer_dropout": 0.0,
  "final_dropout": 0.1,
  "forced_decoder_ids": [
    [
      1,
      50259
    ],
    [
      2,
      50359
    ],
    [
      3,
      50363
    ]
  ],
  "hidden_act": "gelu",
  "hidden_dropout": 0.0,
  "hidden_size": 768,
  "init_std": 0.02,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_encoder_decoder": true,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.0,
  "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,
  "model_type": "wav2vec2",
  "num_adapter_layers": 3,
  "num_attention_heads": 12,
  "num_codevector_groups": 2,
  "num_codevectors_per_group": 320,
  "num_conv_pos_embedding_groups": 16,
  "num_conv_pos_embeddings": 128,
  "num_feat_extract_layers": 7,
  "num_hidden_layers": 12,
  "num_mel_bins": 80,
  "num_negatives": 100,
  "output_hidden_size": 768,
  "pad_token_id": 42,
  "proj_codevector_dim": 256,
  "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
  ],
  "tdnn_dilation": [
    1,
    2,
    3,
    1,
    1
  ],
  "tdnn_dim": [
    512,
    512,
    512,
    512,
    1500
  ],
  "tdnn_kernel": [
    5,
    3,
    3,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 45,
  "xvector_output_dim": 512
}