config.json

{
  "_name_or_path": "openai/whisper-small",
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "adaptor_activation": "relu",
  "adaptor_init": "constant",
  "adaptor_layernorm": true,
  "apply_spec_augment": false,
  "architectures": [
    "WhisperForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50257
  ],
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "crf_transition_matrix": null,
  "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
    ]
  ],
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "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_for_slu",
  "num_hidden_layers": 12,
  "num_mel_bins": 80,
  "pad_token_id": 50257,
  "scale_embedding": false,
  "slu_attention_heads": 12,
  "slu_dropout": 0.3,
  "slu_embed_dim": 768,
  "slu_ffn_dim": 2048,
  "slu_focus": 1.0,
  "slu_input_from": "decoder",
  "slu_input_layers": [
    11
  ],
  "slu_labels": [
    "O",
    "B-cardinal number",
    "B-date",
    "I-date",
    "B-person",
    "I-person",
    "B-group",
    "B-geopolitical area",
    "I-geopolitical area",
    "B-law",
    "I-law",
    "B-organization",
    "I-organization",
    "B-percent",
    "I-percent",
    "B-ordinal number",
    "B-money",
    "I-money",
    "B-work of art",
    "I-work of art",
    "B-facility",
    "B-time",
    "I-cardinal number",
    "B-location",
    "B-quantity",
    "I-quantity",
    "I-group",
    "I-location",
    "B-product",
    "I-time",
    "B-event",
    "I-event",
    "I-facility",
    "B-language",
    "I-product",
    "I-ordinal number",
    "I-language"
  ],
  "slu_layers": 2,
  "slu_max_positions": null,
  "slu_output_dim": 37,
  "slu_pad_token_id": 1,
  "slu_start_token_id": 36,
  "slu_task": "named_entity_recognition",
  "slu_weight": 0.2,
  "special_token_ids": [
    50257,
    50258,
    50259,
    50260,
    50261,
    50262,
    50263,
    50264,
    50265,
    50266,
    50267,
    50268,
    50269,
    50270,
    50271,
    50272,
    50273,
    50274,
    50275,
    50276,
    50277,
    50278,
    50279,
    50280,
    50281,
    50282,
    50283,
    50284,
    50285,
    50286,
    50287,
    50288,
    50289,
    50290,
    50291,
    50292,
    50293,
    50294,
    50295,
    50296,
    50297,
    50298,
    50299,
    50300,
    50301,
    50302,
    50303,
    50304,
    50305,
    50306,
    50307,
    50308,
    50309,
    50310,
    50311,
    50312,
    50313,
    50314,
    50315,
    50316,
    50317,
    50318,
    50319,
    50320,
    50321,
    50322,
    50323,
    50324,
    50325,
    50326,
    50327,
    50328,
    50329,
    50330,
    50331,
    50332,
    50333,
    50334,
    50335,
    50336,
    50337,
    50338,
    50339,
    50340,
    50341,
    50342,
    50343,
    50344,
    50345,
    50346,
    50347,
    50348,
    50349,
    50350,
    50351,
    50352,
    50353,
    50354,
    50355,
    50356,
    50357,
    50358,
    50359,
    50360,
    50361,
    50362,
    50363
  ],
  "task": "token_classification",
  "teacher": null,
  "torch_dtype": "float32",
  "transformers_version": "4.37.0.dev0",
  "use_cache": true,
  "use_crf": false,
  "use_weighted_layer_sum": false,
  "vocab_size": 51865
}