config.json

{
  "architectures": [
    "ParakeetForCTC"
  ],
  "ctc_loss_reduction": "mean",
  "ctc_zero_infinity": true,
  "dtype": "bfloat16",
  "encoder_config": {
    "activation_dropout": 0.1,
    "attention_bias": true,
    "attention_dropout": 0.1,
    "conv_kernel_size": 9,
    "dropout": 0.1,
    "dropout_positions": 0.0,
    "hidden_act": "silu",
    "hidden_size": 1024,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "layerdrop": 0.1,
    "max_position_embeddings": 5000,
    "model_type": "parakeet_encoder",
    "num_attention_heads": 8,
    "num_hidden_layers": 24,
    "num_key_value_heads": 8,
    "num_mel_bins": 80,
    "scale_input": true,
    "subsampling_conv_channels": 256,
    "subsampling_conv_kernel_size": 3,
    "subsampling_conv_stride": 2,
    "subsampling_factor": 8
  },
  "initializer_range": 0.02,
  "model_type": "parakeet_ctc",
  "pad_token_id": 1024,
  "transformers_version": "4.57.0.dev0",
  "vocab_size": 1025
}