config.json

{
  "architectures": [
    "VibeVoiceSemanticTokenizerModel"
  ],
  "causal": true,
  "channels": 1,
  "conv_bias": true,
  "conv_norm": "none",
  "corpus_normalize": 0.0,
  "disable_last_norm": true,
  "encoder_depths": "3-3-3-3-3-3-8",
  "encoder_n_filters": 32,
  "encoder_ratios": [
    8,
    5,
    5,
    4,
    2,
    2
  ],
  "fix_std": 0,
  "layer_scale_init_value": 1e-06,
  "layernorm": "RMSNorm",
  "layernorm_elementwise_affine": true,
  "layernorm_eps": 1e-05,
  "mixer_layer": "depthwise_conv",
  "model_type": "vibevoice_semantic_tokenizer",
  "pad_mode": "constant",
  "std_dist_type": "none",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "vae_dim": 128,
  "weight_init_value": 0.01
}