config.json

{
  "_attn_implementation_autoset": true,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "apply_spec_augment": false,
  "architectures": [
    "WhisperForConditionalGeneration"
  ],
  "attention_dropout": 0.0,
  "begin_suppress_tokens": [
    220,
    50256
  ],
  "bos_token_id": 50257,
  "classifier_proj_size": 256,
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 2,
  "decoder_start_token_id": 50257,
  "dropout": 0.0,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_layerdrop": 0.0,
  "encoder_layers": 24,
  "eos_token_id": 50256,
  "forced_decoder_ids": [
    [
      1,
      50362
    ]
  ],
  "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": null,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "median_filter_width": 7,
  "model_type": "whisper",
  "num_hidden_layers": 24,
  "num_mel_bins": 80,
  "pad_token_id": 50256,
  "scale_embedding": false,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_weighted_layer_sum": false,
  "vocab_size": 51864
}