config.json

{
  "_attn_implementation_autoset": false,
  "acoustic_tokenizer_config": {
    "causal": true,
    "channels": 1,
    "conv_bias": true,
    "conv_norm": "none",
    "corpus_normalize": 0.0,
    "decoder_depths": null,
    "decoder_n_filters": 32,
    "decoder_ratios": [
      8,
      5,
      5,
      4,
      2,
      2
    ],
    "disable_last_norm": true,
    "dtype": "bfloat16",
    "encoder_depths": "3-3-3-3-3-3-8",
    "encoder_n_filters": 32,
    "encoder_ratios": [
      8,
      5,
      5,
      4,
      2,
      2
    ],
    "fix_std": 0.5,
    "layer_scale_init_value": 1e-06,
    "layernorm": "RMSNorm",
    "layernorm_elementwise_affine": true,
    "layernorm_eps": 1e-05,
    "mixer_layer": "depthwise_conv",
    "model_type": "vibevoice_acoustic_tokenizer",
    "pad_mode": "constant",
    "std_dist_type": "gaussian",
    "vae_dim": 64,
    "weight_init_value": 0.01
  },
  "acoustic_vae_dim": 64,
  "architectures": [
    "VibeVoiceForASRTraining"
  ],
  "decoder_config": {
    "attention_dropout": 0.0,
    "dtype": "bfloat16",
    "hidden_act": "silu",
    "hidden_size": 3584,
    "initializer_range": 0.02,
    "intermediate_size": 18944,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 131072,
    "max_window_layers": 28,
    "model_type": "qwen2",
    "num_attention_heads": 28,
    "num_hidden_layers": 28,
    "num_key_value_heads": 4,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000.0,
    "sliding_window": null,
    "use_cache": true,
    "use_mrope": false,
    "use_sliding_window": false,
    "vocab_size": 152064
  },
  "diffusion_head_config": {
    "ddpm_batch_mul": 4,
    "ddpm_beta_schedule": "cosine",
    "ddpm_num_inference_steps": 20,
    "ddpm_num_steps": 1000,
    "diffusion_type": "ddpm",
    "head_ffn_ratio": 3.0,
    "head_layers": 4,
    "hidden_size": 3584,
    "latent_size": 64,
    "model_type": "vibepod_diffusion_head",
    "prediction_type": "v_prediction",
    "rms_norm_eps": 1e-05,
    "speech_vae_dim": 64
  },
  "dtype": "float32",
  "model_type": "vibevoice",
  "semantic_tokenizer_config": {
    "causal": true,
    "channels": 1,
    "conv_bias": true,
    "conv_norm": "none",
    "corpus_normalize": 0.0,
    "disable_last_norm": true,
    "dtype": "bfloat16",
    "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",
    "vae_dim": 128,
    "weight_init_value": 0.01
  },
  "semantic_vae_dim": 128,
  "transformers_version": "4.57.6"
}