{
  "architectures": [
    "MatoubForTextToWaveform"
  ],
  "auto_map": {
    "AutoConfig": "configuration_matoub.MatoubConfig",
    "AutoModel": "modeling_matoub.MatoubForTextToWaveform",
    "AutoModelForTextToWaveform": "modeling_matoub.MatoubForTextToWaveform"
  },
  "dropout": 0.2,
  "dtype": "float32",
  "gen_istft_hop_size": 5,
  "gen_istft_n_fft": 20,
  "hidden_size": 512,
  "max_duration": 50,
  "model_type": "matoub",
  "num_layers": 3,
  "num_mels": 80,
  "pad_token_id": 0,
  "plbert_hidden_size": 768,
  "plbert_intermediate_size": 2048,
  "plbert_max_position_embeddings": 512,
  "plbert_num_attention_heads": 12,
  "plbert_num_hidden_layers": 12,
  "resblock_dilation_sizes": [
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ]
  ],
  "resblock_kernel_sizes": [
    3,
    7,
    11
  ],
  "sampling_rate": 24000,
  "style_dim": 128,
  "text_encoder_kernel_size": 5,
  "transformers_version": "5.12.1",
  "upsample_initial_channel": 512,
  "upsample_kernel_sizes": [
    20,
    12
  ],
  "upsample_rates": [
    10,
    6
  ],
  "vocab_size": 178
}