config.json

{
  "architectures": [
    "ParakeetForTDT"
  ],
  "blank_token_id": 8192,
  "decoder_hidden_size": 640,
  "dtype": "float32",
  "durations": [
    0,
    1,
    2,
    3,
    4
  ],
  "encoder_config": {
    "activation_dropout": 0.1,
    "attention_bias": false,
    "attention_dropout": 0.1,
    "conv_kernel_size": 9,
    "convolution_bias": false,
    "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": 128,
    "scale_input": false,
    "subsampling_conv_channels": 256,
    "subsampling_conv_kernel_size": 3,
    "subsampling_conv_stride": 2,
    "subsampling_factor": 8
  },
  "hidden_act": "relu",
  "initializer_range": 0.02,
  "is_encoder_decoder": true,
  "max_symbols_per_step": 10,
  "model_type": "parakeet_tdt",
  "num_decoder_layers": 2,
  "pad_token_id": 2,
  "transformers_version": "5.15.1",
  "vocab_size": 8193
}