{
  "model": {
    "fm_decoder_downsampling_factor": [
      1,
      2,
      4,
      2,
      1
    ],
    "fm_decoder_num_layers": [
      2,
      2,
      4,
      4,
      4
    ],
    "fm_decoder_cnn_module_kernel": [
      31,
      15,
      7,
      15,
      31
    ],
    "fm_decoder_feedforward_dim": 1536,
    "fm_decoder_num_heads": 4,
    "fm_decoder_dim": 512,
    "text_encoder_num_layers": 4,
    "text_encoder_feedforward_dim": 512,
    "text_encoder_cnn_module_kernel": 9,
    "text_encoder_num_heads": 4,
    "text_encoder_dim": 192,
    "query_head_dim": 32,
    "value_head_dim": 12,
    "pos_head_dim": 4,
    "pos_dim": 48,
    "time_embed_dim": 192,
    "text_embed_dim": 192,
    "feat_dim": 100
  },
  "feature": {
    "type": "vocos",
    "n_fft": 1024,
    "hop_length": 256,
    "n_mels": 100,
    "sample_rate": 24000
  },
  "architectures": [
    "LuxTTSForTextToSpeech"
  ]
}