config.json

{
  "model_type": "xtts_gpt",
  "architectures": [
    "XttsGPT"
  ],
  "vocab_size": 6681,
  "hidden_size": 1024,
  "num_hidden_layers": 30,
  "num_attention_heads": 16,
  "n_inner": 4096,
  "number_text_tokens": 6681,
  "num_audio_tokens": 1026,
  "max_audio_tokens": 605,
  "start_audio_token": 1024,
  "stop_audio_token": 1025,
  "max_text_tokens": 402,
  "max_prompt_tokens": 70,
  "activation_function": "gelu_new",
  "attn_pdrop": 0.1,
  "layer_norm_epsilon": 1e-05,
  "initializer_range": 0.02,
  "use_masking_gt_prompt_approach": true,
  "use_perceiver_resampler": true,
  "kv_cache": true,
  "enable_redaction": false,
  "reorder_and_upcast_attn": false,
  "scale_attn_by_inverse_layer_idx": false,
  "auto_map": {
    "AutoConfig": "AstraMindAI/xtts2-gpt--gpt_config.XTTSGPTConfig",
    "AutoModelForCausalLM": "AstraMindAI/xtts2-gpt--xtts2_gpt_modeling.XttsGPT",
    "AutoTokenizer": "AstraMindAI/xtts2-gpt--tokenizer.XTTSTokenizerFast"
  },
  "languages": [
    "en",
    "es",
    "fr",
    "de",
    "it",
    "pt",
    "pl",
    "tr",
    "ru",
    "nl",
    "cs",
    "ar",
    "zh-cn",
    "hu",
    "ko",
    "ja",
    "hi"
  ]
}