config.json

{
  "architectures": [
    "ArkttsModel"
  ],
  "attention_o_bias": false,
  "attention_qk_norm": false,
  "attention_qkv_bias": true,
  "auto_map": {
    "AutoConfig": "configuration_arktts.ArkttsConfig",
    "AutoModel": "modeling_arktts.ArkttsModel",
    "AutoModelForCausalLM": "modeling_arktts.ArkttsModel"
  },
  "codebook_size": 4096,
  "codec_filename": "codec.pth",
  "codec_frame_size": 2048,
  "codec_post_intermediate_size": 1216,
  "codec_post_n_head": 16,
  "codec_post_n_layer": 8,
  "codec_post_n_local_heads": 8,
  "codec_sample_rate": 44100,
  "dim": 896,
  "dropout": 0.0,
  "dtype": "bfloat16",
  "eos_token_id": 151645,
  "fast_attention_o_bias": false,
  "fast_attention_qk_norm": false,
  "fast_attention_qkv_bias": false,
  "fast_dim": 896,
  "fast_head_dim": 64,
  "fast_intermediate_size": 4864,
  "fast_n_head": 14,
  "fast_n_local_heads": 2,
  "head_dim": 64,
  "initializer_range": 0.02,
  "intermediate_size": 4864,
  "max_seq_len": 2048,
  "model_type": "arktts",
  "n_fast_layer": 4,
  "n_head": 14,
  "n_layer": 24,
  "n_local_heads": 2,
  "norm_eps": 1e-06,
  "norm_fastlayer_input": true,
  "num_codebooks": 10,
  "pad_token_id": 151643,
  "ras_temperature": 1.0,
  "ras_top_p": 0.9,
  "ras_window_size": 10,
  "rope_base": 1000000,
  "semantic_begin_id": 151678,
  "semantic_end_id": 155773,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.5",
  "use_gradient_checkpointing": false,
  "vocab_size": 155776
}