config.json

{
  "activation_dropout": 0.1,
  "architectures": [
    "VitsModelForPreTraining"
  ],
  "attention_dropout": 0.1,
  "depth_separable_channels": 2,
  "depth_separable_num_layers": 3,
  "discriminator_kernel_size": 5,
  "discriminator_period_channels": [
    1,
    32,
    128,
    512,
    1024
  ],
  "discriminator_periods": [
    2,
    3,
    5,
    7,
    11
  ],
  "discriminator_scale_channels": [
    1,
    16,
    64,
    256,
    1024
  ],
  "discriminator_stride": 3,
  "duration_predictor_dropout": 0.5,
  "duration_predictor_filter_channels": 256,
  "duration_predictor_flow_bins": 10,
  "duration_predictor_kernel_size": 3,
  "duration_predictor_num_flows": 4,
  "duration_predictor_tail_bound": 5.0,
  "ffn_dim": 768,
  "ffn_kernel_size": 3,
  "flow_size": 192,
  "hidden_act": "relu",
  "hidden_dropout": 0.1,
  "hidden_size": 192,
  "hop_length": 256,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-05,
  "layerdrop": 0.1,
  "leaky_relu_slope": 0.1,
  "model_type": "vits",
  "noise_scale": 0.667,
  "noise_scale_duration": 0.8,
  "num_attention_heads": 2,
  "num_hidden_layers": 6,
  "num_speakers": 1,
  "posterior_encoder_num_wavenet_layers": 16,
  "prior_encoder_num_flows": 4,
  "prior_encoder_num_wavenet_layers": 4,
  "resblock_dilation_sizes": [
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ]
  ],
  "resblock_kernel_sizes": [
    3,
    7,
    11
  ],
  "sampling_rate": 16000,
  "segment_size": 8192,
  "speaker_embedding_size": 0,
  "speaking_rate": 1.0,
  "spectrogram_bins": 513,
  "torch_dtype": "float32",
  "transformers_version": "4.42.4",
  "upsample_initial_channel": 512,
  "upsample_kernel_sizes": [
    16,
    16,
    4,
    4
  ],
  "upsample_rates": [
    8,
    8,
    2,
    2
  ],
  "use_bias": true,
  "use_stochastic_duration_prediction": true,
  "vocab_size": 39,
  "wavenet_dilation_rate": 1,
  "wavenet_dropout": 0.0,
  "wavenet_kernel_size": 5,
  "window_size": 4
}