{
  "activation_dropout": 0.1,
  "activation_function": "relu",
  "architectures": [
    "ConformerEncoderDecoderForConditionalGeneration"
  ],
  "attention_dropout": 0.1,
  "auto_map": {
    "AutoConfig": "configuration_conformer.Speech2TextConformerConfig",
    "AutoModelForSpeechSeq2Seq": "conformer_model.ConformerEncoderDecoderForConditionalGeneration"
  },
  "batch_unsafe_relative_shift": true,
  "bos_token_id": 0,
  "conformer_attention_dropout": 0.1,
  "conformer_conv_dropout": 0.1,
  "conformer_conv_kernel_size": 31,
  "conformer_feedforward_dropout": 0.1,
  "conformer_half_step_residual": true,
  "conv_channels": 1024,
  "conv_expansion_factor": 2,
  "conv_kernel_sizes": [
    5,
    5
  ],
  "ctc_compress_fixed_ratio": 4,
  "ctc_compress_max_out_size": -1,
  "ctc_compress_strategy": "none",
  "d_model": 1024,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_layerdrop": 0.0,
  "decoder_layers": 6,
  "decoder_start_token_id": 2,
  "dropout": 0.1,
  "early_stopping": null,
  "encoder_attention_heads": 16,
  "encoder_layers": 12,
  "eos_token_id": 2,
  "feed_forward_expansion_factor": 4,
  "init_std": 0.02,
  "input_channels": 1,
  "input_feat_per_channel": 80,
  "is_encoder_decoder": true,
  "max_length": null,
  "max_source_positions": 3000,
  "max_target_positions": 512,
  "model_type": "conformer_encoder_decoder",
  "no_syncbatchnorm": false,
  "num_beams": null,
  "num_conv_layers": 2,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "scale_embedding": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.48.1",
  "use_cache": true,
  "vocab_size": 16004
}