config.json

{
  "model_type": "xtts",
  "audio": {
    "sample_rate": 22050,
    "output_sample_rate": 24000,
    "dvae_sample_rate": 22050
  },
  "model_args": {
    "gpt_batch_size": 1,
    "enable_redaction": false,
    "kv_cache": true,
    "gpt_checkpoint": "model.pth",
    "clvp_checkpoint": null,
    "decoder_checkpoint": null,
    "num_chars": 255,
    "tokenizer_file": "vocab.json",
    "gpt_max_audio_tokens": 605,
    "gpt_max_text_tokens": 402,
    "gpt_max_prompt_tokens": 70,
    "gpt_layers": 30,
    "gpt_n_model_channels": 1024,
    "gpt_n_heads": 16,
    "gpt_number_text_tokens": 8456,
    "gpt_start_text_token": 261,
    "gpt_stop_text_token": 0,
    "gpt_num_audio_tokens": 1026,
    "gpt_start_audio_token": 1024,
    "gpt_stop_audio_token": 1025,
    "gpt_code_stride_len": 1024,
    "gpt_use_masking_gt_prompt_approach": true,
    "gpt_use_perceiver_resampler": true,
    "input_sample_rate": 22050,
    "output_sample_rate": 24000,
    "output_hop_length": 256,
    "decoder_input_dim": 1024,
    "d_vector_dim": 512,
    "cond_d_vector_in_each_upsampling_layer": true,
    "duration_const": 102400,
    "min_conditioning_length": 11025,
    "max_conditioning_length": 132300,
    "gpt_loss_text_ce_weight": 0.01,
    "gpt_loss_mel_ce_weight": 1.0,
    "debug_loading_failures": false,
    "max_wav_length": 330750,
    "max_text_length": 400,
    "mel_norm_file": "mel_stats.pth",
    "dvae_checkpoint": "dvae.pth",
    "xtts_checkpoint": "model.pth",
    "vocoder": ""
  },
  "languages": [
    "en",
    "es", 
    "fr",
    "de",
    "it",
    "pt",
    "pl",
    "tr",
    "ru",
    "nl",
    "cs",
    "ar",
    "zh-cn",
    "hu",
    "ko",
    "ja",
    "hi",
    "mns"
  ],
  "temperature": 0.75,
  "length_penalty": 1.0,
  "repetition_penalty": 5.0,
  "top_k": 50,
  "top_p": 0.85,
  "num_gpt_outputs": 1,
  "gpt_cond_len": 30,
  "gpt_cond_chunk_len": 4,
  "max_ref_len": 30,
  "sound_norm_refs": false
}