config.json

{
    "model": "vits",
    "run_name": "vits_ljspeech",
    "run_description": "",
    "epochs": 1000,
    "batch_size": 18,
    "eval_batch_size": 16,
    "mixed_precision": true,
    "scheduler_after_epoch": true,
    "run_eval": true,
    "test_delay_epochs": -1,
    "print_eval": true,
    "dashboard_logger": "tensorboard",
    "print_step": 25,
    "plot_step": 100,
    "model_param_stats": false,
    "project_name": null,
    "log_model_step": null,
    "wandb_entity": null,
    "save_step": 10000,
    "checkpoint": true,
    "keep_all_best": false,
    "keep_after": 10000,
    "num_loader_workers": 12,
    "num_eval_loader_workers": 12,
    "use_noise_augment": false,
    "output_path": "./ukrainian-vits",
    "distributed_backend": "nccl",
    "distributed_url": "tcp://localhost:54321",
    "audio": {
        "fft_size": 1024,
        "win_length": 1024,
        "hop_length": 256,
        "frame_shift_ms": null,
        "frame_length_ms": null,
        "stft_pad_mode": "reflect",
        "sample_rate": 16000,
        "resample": false,
        "preemphasis": 0.0,
        "ref_level_db": 20,
        "do_sound_norm": false,
        "log_func": "np.log",
        "do_trim_silence": true,
        "trim_db": 45,
        "power": 1.3,
        "griffin_lim_iters": 60,
        "num_mels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": null,
        "spec_gain": 1,
        "do_amp_to_db_linear": false,
        "do_amp_to_db_mel": true,
        "signal_norm": false,
        "min_level_db": -100,
        "symmetric_norm": true,
        "max_norm": 4.0,
        "clip_norm": true,
        "stats_path": null
    },
    "use_phonemes": false,
    "use_espeak_phonemes": true,
    "phoneme_language": null,
    "compute_input_seq_cache": true,
    "text_cleaner": "basic_cleaners",
    "enable_eos_bos_chars": false,
    "test_sentences_file": "",
    "phoneme_cache_path": "./ukrainian/phoneme_cache",
    "characters": {
        "pad": "_",
        "eos": "~",
        "bos": "^",
        "characters": "!',-.:;?\u0410\u0411\u0412\u0413\u0490\u0414\u0415\u0404\u0416\u0417\u0418\u0406\u0407\u0419\u041a\u041b\u041c\u041d\u041e\u041f\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042c\u042e\u042f\u0430\u0431\u0432\u0433\u0491\u0434\u0435\u0454\u0436\u0437\u0438\u0456\u0457\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044c\u044e\u044f ",
        "punctuations": "!',-.:;? ",
        "phonemes": null,
        "unique": true
    },
    "batch_group_size": 5,
    "loss_masking": null,
    "sort_by_audio_len": true,
    "min_seq_len": 0,
    "max_seq_len": 500000,
    "compute_f0": false,
    "compute_linear_spec": true,
    "add_blank": true,
    "datasets": [
        {
            "name": "ljspeech",
            "path": "./Data/uk_UK/by_book/female/sumska/kaydasheva",
            "meta_file_train": "metadata.csv",
            "ununsed_speakers": null,
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        },
        {
            "name": "ljspeech",
            "path": "./Data/uk_UK/by_book/female/sumska/mykola_djerya",
            "meta_file_train": "metadata.csv",
            "ununsed_speakers": null,
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        }
    ],
    "optimizer": "AdamW",
    "optimizer_params": {
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-09,
        "weight_decay": 0.01
    },
    "lr_scheduler": "",
    "lr_scheduler_params": {},
    "test_sentences": [
        "\u0413\u043e\u0432\u043e\u0440\u0438 \u043d\u0456\u0431\u0438 \u0442\u0438 \u0436\u0438\u0432\u0438\u0439!",
        "\u041f\u043e\u043b \u043f\u0435\u0440\u0435\u0442\u043d\u0443\u0432 \u043f\u0443\u0441\u0442\u0435\u043b\u044e",
        "\u041f\u0440\u0438\u0432\u0456\u0442, \u0441\u0432\u0456\u0442\u0435!"
    ],
    "model_args": {
        "num_chars": 86,
        "out_channels": 513,
        "spec_segment_size": 24,
        "hidden_channels": 192,
        "hidden_channels_ffn_text_encoder": 768,
        "num_heads_text_encoder": 2,
        "num_layers_text_encoder": 6,
        "kernel_size_text_encoder": 3,
        "dropout_p_text_encoder": 0.1,
        "dropout_p_duration_predictor": 0.5,
        "kernel_size_posterior_encoder": 5,
        "dilation_rate_posterior_encoder": 1,
        "num_layers_posterior_encoder": 16,
        "kernel_size_flow": 5,
        "dilation_rate_flow": 1,
        "num_layers_flow": 4,
        "resblock_type_decoder": "1",
        "resblock_kernel_sizes_decoder": [
            3,
            7,
            11
        ],
        "resblock_dilation_sizes_decoder": [
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ]
        ],
        "upsample_rates_decoder": [
            8,
            8,
            2,
            2
        ],
        "upsample_initial_channel_decoder": 512,
        "upsample_kernel_sizes_decoder": [
            16,
            16,
            4,
            4
        ],
        "use_sdp": true,
        "noise_scale": 1.0,
        "inference_noise_scale": 0.667,
        "length_scale": 1.0,
        "noise_scale_dp": 1.0,
        "inference_noise_scale_dp": 1.0,
        "max_inference_len": null,
        "init_discriminator": true,
        "use_spectral_norm_disriminator": false,
        "use_speaker_embedding": false,
        "num_speakers": 0,
        "speakers_file": null,
        "speaker_embedding_channels": 256,
        "use_d_vector_file": false,
        "d_vector_file": null,
        "d_vector_dim": 0,
        "detach_dp_input": true
    },
    "grad_clip": [
        1000.0,
        1000.0
    ],
    "lr_gen": 0.0002,
    "lr_disc": 0.0002,
    "lr_scheduler_gen": "ExponentialLR",
    "lr_scheduler_gen_params": {
        "gamma": 0.999875,
        "last_epoch": -1
    },
    "lr_scheduler_disc": "ExponentialLR",
    "lr_scheduler_disc_params": {
        "gamma": 0.999875,
        "last_epoch": -1
    },
    "kl_loss_alpha": 1.0,
    "disc_loss_alpha": 1.0,
    "gen_loss_alpha": 1.0,
    "feat_loss_alpha": 1.0,
    "mel_loss_alpha": 45.0,
    "dur_loss_alpha": 1.0,
    "return_wav": true,
    "r": 1,
    "num_speakers": 0,
    "use_speaker_embedding": false,
    "speakers_file": null,
    "speaker_embedding_channels": 256,
    "use_d_vector_file": false,
    "d_vector_file": null,
    "d_vector_dim": 0
}