{
  "architectures": [
    "PocketTTSAudioTokenizerModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_channels": 1,
  "compress": 2,
  "dilation_growth_rate": 2,
  "dtype": "float32",
  "encoder_config": null,
  "head_dim": 64,
  "hidden_act": "gelu",
  "hidden_size": 512,
  "initializer_range": 0.02,
  "intermediate_size": 2048,
  "kernel_size": 7,
  "last_kernel_size": 3,
  "latent_dim": 32,
  "latent_stride": 16,
  "layer_scale_initial_scale": 0.01,
  "max_position_embeddings": 8000,
  "model_type": "pocket_tts_audio_tokenizer",
  "norm_eps": 1e-05,
  "num_attention_heads": 8,
  "num_filters": 64,
  "num_hidden_layers": 2,
  "num_key_value_heads": 8,
  "num_residual_layers": 1,
  "pad_mode": "constant",
  "residual_kernel_size": 3,
  "rope_parameters": {
    "rope_theta": 10000.0,
    "rope_type": "default"
  },
  "sampling_rate": 24000,
  "sliding_window": 251,
  "transformers_version": "5.21.0.dev0",
  "trim_right_ratio": 1.0,
  "upsample_groups": 512,
  "upsampling_ratios": [
    6,
    5,
    4
  ],
  "use_cache": false,
  "use_causal_conv": true,
  "use_conv_shortcut": false,
  "use_streaming": false
}