config.json

{
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperCTCforTransformers"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50256
  ],
  "blank_token_id": 42,
  "bos_token_id": 50256,
  "classifier_proj_size": 256,
  "ctc_loss_reduction": "mean",
  "ctc_zero_infinity": false,
  "d_model": 384,
  "decoder_attention_heads": 6,
  "decoder_end_token_id": 41,
  "decoder_ffn_dim": 1536,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 1,
  "decoder_size": 43,
  "decoder_start_token_id": 40,
  "dropout": 0.0,
  "encoder_attention_heads": 6,
  "encoder_ffn_dim": 1536,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 4,
  "eos_token_id": 50256,
  "feature_size": 80,
  "init_std": 0.02,
  "is_encoder_decoder": true,
  "lexicon_path": "./lexicon.txt",
  "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_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 4,
  "num_mel_bins": 80,
  "pad_token_id": 42,
  "scale_embedding": false,
  "size": "tiny",
  "tokens": [
    "SIL",
    "AA",
    "AE",
    "AH",
    "AO",
    "AW",
    "AX",
    "AY",
    "B",
    "CH",
    "D",
    "DH",
    "EH",
    "ER",
    "EY",
    "F",
    "G",
    "HH",
    "IH",
    "IY",
    "JH",
    "K",
    "L",
    "M",
    "N",
    "NG",
    "OW",
    "OY",
    "P",
    "R",
    "S",
    "SH",
    "T",
    "TH",
    "UH",
    "UW",
    "V",
    "W",
    "Y",
    "Z",
    "ZH",
    "<S>",
    "</S>"
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.52.3",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51864
}