speech_tokenizer/config.json

{
  "architectures": [
    "Qwen3TTSTokenizerV2Model"
  ],
  "model_type": "qwen3_tts_tokenizer_12hz",
  "encoder_valid_num_quantizers": 16,
  "input_sample_rate": 24000,
  "output_sample_rate": 24000,
  "decode_upsample_rate": 1920,
  "encode_downsample_rate": 1920,
  "decoder_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "latent_dim": 1024,
    "codebook_dim": 512,
    "codebook_size": 2048,
    "decoder_dim": 1536,
    "hidden_act": "silu",
    "hidden_size": 512,
    "intermediate_size": 1024,
    "layer_scale_initial_scale": 0.01,
    "max_position_embeddings": 8000,
    "head_dim": 64,
    "num_attention_heads": 16,
    "num_hidden_layers": 8,
    "num_key_value_heads": 16,
    "num_quantizers": 16,
    "num_semantic_quantizers": 1,
    "rms_norm_eps": 1e-05,
    "rope_theta": 10000,
    "semantic_codebook_size": 4096,
    "sliding_window": 72,
    "upsample_rates": [
      8,
      5,
      4,
      3
    ],
    "upsampling_ratios": [
      2,
      2
    ],
    "vector_quantization_hidden_dimension": 512
  },
  "encoder_config": {
    "_frame_rate": 12.5,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "audio_channels": 1,
    "codebook_dim": 256,
    "codebook_size": 2048,
    "compress": 2,
    "dilation_growth_rate": 2,
    "dtype": "float32",
    "head_dim": 64,
    "hidden_act": "gelu",
    "hidden_size": 512,
    "initializer_range": 0.02,
    "intermediate_size": 2048,
    "kernel_size": 7,
    "last_kernel_size": 3,
    "layer_scale_initial_scale": 0.01,
    "max_position_embeddings": 8000,
    "norm_eps": 1e-05,
    "normalize": false,
    "num_attention_heads": 8,
    "num_filters": 64,
    "num_hidden_layers": 8,
    "num_key_value_heads": 8,
    "num_quantizers": 32,
    "num_residual_layers": 1,
    "num_semantic_quantizers": 1,
    "pad_mode": "constant",
    "residual_kernel_size": 3,
    "rope_theta": 10000.0,
    "sampling_rate": 24000,
    "sliding_window": 250,
    "transformers_version": "4.57.0.dev0",
    "trim_right_ratio": 1.0,
    "upsample_groups": 512,
    "upsampling_ratios": [
      8,
      6,
      5,
      4
    ],
    "use_cache": false,
    "use_causal_conv": true,
    "use_conv_shortcut": false,
    "use_streaming": false,
    "vector_quantization_hidden_dimension": 256
  },
  "transformers_version": "4.57.3"
}