{
  "activation_dropout": 0.1,
  "architectures": [
    "LasrEncoder"
  ],
  "attention_bias": false,
  "attention_dropout": 0.1,
  "batch_norm_momentum": 0.01,
  "conv_kernel_size": 8,
  "conv_residual_weights": [
    2.0,
    1.0
  ],
  "convolution_bias": false,
  "dropout": 0.1,
  "dropout_positions": 0.0,
  "dtype": "float32",
  "feed_forward_residual_weights": [
    1.5,
    0.5
  ],
  "hidden_act": "silu",
  "hidden_size": 64,
  "initializer_range": 0.02,
  "intermediate_size": 256,
  "layer_norm_eps": 1e-06,
  "layerdrop": 0.0,
  "max_position_embeddings": 512,
  "model_type": "lasr_encoder",
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 4,
  "num_mel_bins": 80,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "subsampling_conv_channels": 32,
  "subsampling_conv_kernel_size": 5,
  "subsampling_conv_stride": 2,
  "transformers_version": "5.16.0.dev0"
}