config.json

{
    "output_path": "output",
    "logger_uri": null,
    "run_name": "run",
    "project_name": null,
    "run_description": "\ud83d\udc38Coqui trainer run.",
    "print_step": 25,
    "plot_step": 100,
    "model_param_stats": false,
    "wandb_entity": null,
    "dashboard_logger": "tensorboard",
    "save_on_interrupt": true,
    "log_model_step": null,
    "save_step": 10000,
    "save_n_checkpoints": 5,
    "save_checkpoints": true,
    "save_all_best": false,
    "save_best_after": 10000,
    "target_loss": null,
    "print_eval": false,
    "test_delay_epochs": 0,
    "run_eval": true,
    "run_eval_steps": null,
    "distributed_backend": "nccl",
    "distributed_url": "tcp://localhost:54321",
    "mixed_precision": false,
    "precision": "fp16",
    "epochs": 1000,
    "batch_size": 32,
    "eval_batch_size": 16,
    "grad_clip": 0.0,
    "scheduler_after_epoch": true,
    "lr": 0.001,
    "optimizer": "radam",
    "optimizer_params": null,
    "lr_scheduler": null,
    "lr_scheduler_params": {},
    "use_grad_scaler": false,
    "allow_tf32": false,
    "cudnn_enable": true,
    "cudnn_deterministic": false,
    "cudnn_benchmark": false,
    "training_seed": 54321,
    "model": "xtts",
    "num_loader_workers": 0,
    "num_eval_loader_workers": 0,
    "use_noise_augment": false,
    "audio": {
        "sample_rate": 22050,
        "diffusion_sample_rate": 24000,
        "output_sample_rate": 24000
    },
    "use_phonemes": false,
    "phonemizer": null,
    "phoneme_language": null,
    "compute_input_seq_cache": false,
    "text_cleaner": null,
    "enable_eos_bos_chars": false,
    "test_sentences_file": "",
    "phoneme_cache_path": null,
    "characters": null,
    "add_blank": false,
    "batch_group_size": 0,
    "loss_masking": null,
    "min_audio_len": 1,
    "max_audio_len": Infinity,
    "min_text_len": 1,
    "max_text_len": Infinity,
    "compute_f0": false,
    "compute_energy": false,
    "compute_linear_spec": false,
    "precompute_num_workers": 0,
    "start_by_longest": false,
    "shuffle": false,
    "drop_last": false,
    "datasets": [
        {
            "formatter": "",
            "dataset_name": "",
            "path": "",
            "meta_file_train": "",
            "ignored_speakers": null,
            "language": "",
            "phonemizer": "",
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        }
    ],
    "test_sentences": [],
    "eval_split_max_size": null,
    "eval_split_size": 0.01,
    "use_speaker_weighted_sampler": false,
    "speaker_weighted_sampler_alpha": 1.0,
    "use_language_weighted_sampler": false,
    "language_weighted_sampler_alpha": 1.0,
    "use_length_weighted_sampler": false,
    "length_weighted_sampler_alpha": 1.0,
    "model_args": {
        "gpt_batch_size": 1,
        "enable_redaction": false,
        "kv_cache": true,
        "gpt_checkpoint": null,
        "clvp_checkpoint": null,
        "decoder_checkpoint": null,
        "num_chars": 255,
        "use_hifigan": true,
        "use_ne_hifigan": false,
        "tokenizer_file": "",
        "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": 6153,
        "gpt_start_text_token": null,
        "gpt_stop_text_token": null,
        "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,
        "diff_model_channels": 1024,
        "diff_num_layers": 10,
        "diff_in_channels": 100,
        "diff_out_channels": 200,
        "diff_in_latent_channels": 1024,
        "diff_in_tokens": 8193,
        "diff_dropout": 0,
        "diff_use_fp16": false,
        "diff_num_heads": 16,
        "diff_layer_drop": 0,
        "diff_unconditioned_percentage": 0,
        "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
    },
    "model_dir": null,
    "languages": [
        "en",
        "es",
        "fr",
        "de",
        "it",
        "pt",
        "pl",
        "tr",
        "ru",
        "nl",
        "cs",
        "ar",
        "zh-cn",
        "hu",
        "ko",
        "ja"
    ],
    "temperature": 0.65,
    "length_penalty": 1.0,
    "repetition_penalty": 2.0,
    "top_k": 50,
    "top_p": 0.85,
    "cond_free_k": 2.0,
    "diffusion_temperature": 1.0,
    "num_gpt_outputs": 1,
    "decoder_iterations": 30,
    "decoder_sampler": "ddim",
    "gpt_cond_len": 30,
    "max_ref_len": 30,
    "sound_norm_refs": false
}