config.json

{
	"model": "bark",
    "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",
    "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,
    "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,
    "cudnn_enable": true,
    "cudnn_deterministic": false,
    "cudnn_benchmark": false,
    "training_seed": 54321,
    "num_loader_workers": 0,
    "num_eval_loader_workers": 0,
    "use_noise_augment": false,
    "audio": {
        "fft_size": 1024,
        "win_length": 1024,
        "hop_length": 256,
        "frame_shift_ms": null,
        "frame_length_ms": null,
        "stft_pad_mode": "reflect",
        "sample_rate": 22050,
        "resample": false,
        "preemphasis": 0.0,
        "ref_level_db": 20,
        "do_sound_norm": false,
        "log_func": "np.log10",
        "do_trim_silence": true,
        "trim_db": 45,
        "do_rms_norm": false,
        "db_level": null,
        "power": 1.5,
        "griffin_lim_iters": 60,
        "num_mels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": null,
        "spec_gain": 20,
        "do_amp_to_db_linear": true,
        "do_amp_to_db_mel": true,
        "pitch_fmax": 640.0,
        "pitch_fmin": 1.0,
        "signal_norm": true,
        "min_level_db": -100,
        "symmetric_norm": true,
        "max_norm": 4.0,
        "clip_norm": true,
        "stats_path": null
    },
    "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,
    "num_chars": 0,
    "semantic_config": {
        "block_size": 1024,
        "input_vocab_size": 10048,
        "output_vocab_size": 10048,
        "n_layer": 12,
        "n_head": 12,
        "n_embd": 768,
        "dropout": 0.0,
        "bias": true
    },
    "fine_config": {
        "block_size": 1024,
        "input_vocab_size": 10048,
        "output_vocab_size": 10048,
        "n_layer": 12,
        "n_head": 12,
        "n_embd": 768,
        "dropout": 0.0,
        "bias": true,
        "n_codes_total": 8,
        "n_codes_given": 1
    },
    "coarse_config": {
        "block_size": 1024,
        "input_vocab_size": 10048,
        "output_vocab_size": 10048,
        "n_layer": 12,
        "n_head": 12,
        "n_embd": 768,
        "dropout": 0.0,
        "bias": true
    },
    "CONTEXT_WINDOW_SIZE": 1024,
    "SEMANTIC_RATE_HZ": 49.9,
    "SEMANTIC_VOCAB_SIZE": 10000,
    "CODEBOOK_SIZE": 1024,
    "N_COARSE_CODEBOOKS": 2,
    "N_FINE_CODEBOOKS": 8,
    "COARSE_RATE_HZ": 75,
    "SAMPLE_RATE": 24000,
    "USE_SMALLER_MODELS": false,
    "TEXT_ENCODING_OFFSET": 10048,
    "SEMANTIC_PAD_TOKEN": 10000,
    "TEXT_PAD_TOKEN": 129595,
    "SEMANTIC_INFER_TOKEN": 129599,
    "COARSE_SEMANTIC_PAD_TOKEN": 12048,
    "COARSE_INFER_TOKEN": 12050,
    "REMOTE_MODEL_PATHS": {
        "text": {
            "path": "https://huggingface.co/erogol/bark/tree/main/text_2.pt",
            "checksum": "54afa89d65e318d4f5f80e8e8799026a"
        },
        "coarse": {
            "path": "https://huggingface.co/erogol/bark/tree/main/coarse_2.pt",
            "checksum": "8a98094e5e3a255a5c9c0ab7efe8fd28"
        },
        "fine": {
            "path": "https://huggingface.co/erogol/bark/tree/main/fine_2.pt",
            "checksum": "59d184ed44e3650774a2f0503a48a97b"
        }
    },
    "LOCAL_MODEL_PATHS": {
        "text": "/root/.local/share/tts/suno/bark_v0/text_2.pt",
        "coarse": "/root/.local/share/tts/suno/bark_v0/coarse_2.pt",
        "fine": "/root/.local/share/tts/suno/bark_v0/fine_2.pt",
        "hubert_tokenizer": "/root/.local/share/tts/suno/bark_v0/tokenizer.pth",
        "hubert": "/root/.local/share/tts/suno/bark_v0/hubert.pt"
    },
    "SMALL_REMOTE_MODEL_PATHS": {
        "text": {
            "path": "https://huggingface.co/erogol/bark/tree/main/text.pt"
        },
        "coarse": {
            "path": "https://huggingface.co/erogol/bark/tree/main/coarse.pt"
        },
        "fine": {
            "path": "https://huggingface.co/erogol/bark/tree/main/fine.pt"
        }
    },
    "CACHE_DIR": "/root/.local/share/tts/suno/bark_v0"
}