config.json

{
  "vocab_size": 51866,
  "num_mel_bins": 128,
  "d_model": 1280,
  "encoder_layers": 32,
  "encoder_attention_heads": 20,
  "decoder_layers": 4,
  "decoder_attention_heads": 20,
  "decoder_ffn_dim": 5120,
  "encoder_ffn_dim": 5120,
  "dropout": 0.0,
  "attention_dropout": 0.0,
  "activation_dropout": 0.0,
  "activation_function": "gelu",
  "init_std": 0.02,
  "encoder_layerdrop": 0.0,
  "decoder_layerdrop": 0.0,
  "use_cache": true,
  "num_hidden_layers": 32,
  "scale_embedding": false,
  "max_source_positions": 1500,
  "max_target_positions": 448,
  "classifier_proj_size": 256,
  "use_weighted_layer_sum": false,
  "apply_spec_augment": false,
  "mask_time_prob": 0.05,
  "mask_time_length": 10,
  "mask_time_min_masks": 2,
  "mask_feature_prob": 0.0,
  "mask_feature_length": 10,
  "mask_feature_min_masks": 0,
  "median_filter_width": 7,
  "return_dict": true,
  "output_hidden_states": false,
  "output_attentions": false,
  "torchscript": false,
  "torch_dtype": "float16",
  "use_bfloat16": false,
  "tf_legacy_loss": false,
  "pruned_heads": {},
  "tie_word_embeddings": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": true,
  "is_decoder": false,
  "cross_attention_hidden_size": null,
  "add_cross_attention": false,
  "tie_encoder_decoder": false,
  "max_length": 20,
  "min_length": 0,
  "do_sample": false,
  "early_stopping": false,
  "num_beams": 1,
  "num_beam_groups": 1,
  "diversity_penalty": 0.0,
  "temperature": 1.0,
  "top_k": 50,
  "top_p": 1.0,
  "typical_p": 1.0,
  "repetition_penalty": 1.0,
  "length_penalty": 1.0,
  "no_repeat_ngram_size": 0,
  "encoder_no_repeat_ngram_size": 0,
  "bad_words_ids": null,
  "num_return_sequences": 1,
  "output_scores": false,
  "return_dict_in_generate": false,
  "forced_bos_token_id": null,
  "forced_eos_token_id": null,
  "remove_invalid_values": false,
  "exponential_decay_length_penalty": null,
  "suppress_tokens": null,
  "begin_suppress_tokens": [
    220,
    50256
  ],
  "architectures": [
    "WhisperForConditionalGeneration"
  ],
  "finetuning_task": null,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1"
  },
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1
  },
  "tokenizer_class": null,
  "prefix": null,
  "bos_token_id": 50257,
  "pad_token_id": 50257,
  "eos_token_id": 50257,
  "sep_token_id": null,
  "decoder_start_token_id": 0,
  "task_specific_params": null,
  "problem_type": null,
  "_name_or_path": "openai/whisper-large-v3-turbo",
  "_attn_implementation_autoset": true,
  "transformers_version": "4.51.3",
  "model_type": "syllable_whisper",
  "encoder_type": "whisper",
  "freeze_wav2vec": true,
  "phoneme_vocab_size": 55,
  "syllable_vocab_size": 1207,
  "loss_lambda": 0.5,
  "alignment_lambda": 0.5,
  "phoneme_grouping_size": 3,
  "phoneme_pad_token_id": 0,
  "phoneme_bos_token_id": 1,
  "phoneme_eos_token_id": 2,
  "syllable_pad_token_id": 0,
  "syllable_bos_token_id": 1,
  "syllable_eos_token_id": 2,
  "num_layer_stacks": 1,
  "noise_std": 0.01,
  "apply_noise_to_original": false,
  "original_encoder_layers": 32,
  "unfreeze_top_k_layers": 0,
  "original_decoder_layers": 4,
  "reduce_encoder_layers": false,
  "reduce_decoder_layers": false,
  "encoder_layers_to_keep": 32,
  "decoder_layers_to_keep": 4,
  "decoder_dropout_rate": 0.0,
  "decoder_dropout_type": "standard",
  "apply_dropout_to_stacked_only": false,
  "use_encoder_adapter": false,
  "adapter_size": 64,
  "adapter_location": "all",
  "adapter_activation": "relu",
  "adapter_dropout": 0.1,
  "use_parallel_adapter": false
}