config/vits.json

{
    "base_config": "config/tts.json",
    "model_type": "VITS",
    "task_type": "tts",
    "preprocess": {
        "extract_phone": true,
        "extract_mel": true,
        "n_mel": 80,
        "fmin": 0,
        "fmax": null,
        "extract_linear_spec": true,
        "extract_audio": true,
        "use_linear": true,
        "use_mel": true,
        "use_audio": true,
        "use_text": false,
        "use_phone": true,
        "lexicon_path": "./text/lexicon/librispeech-lexicon.txt",
        "n_fft": 1024,
        "win_size": 1024,
        "hop_size": 256,
        "segment_size": 8192,
        "text_cleaners": [
            "english_cleaners"
        ]
    },
    "model": {
        "text_token_num": 512,
        "inter_channels": 192,
        "hidden_channels": 192,
        "filter_channels": 768,
        "n_heads": 2,
        "n_layers": 6,
        "kernel_size": 3,
        "p_dropout": 0.1,
        "resblock": "1",
        "resblock_kernel_sizes": [
            3,
            7,
            11
        ],
        "resblock_dilation_sizes": [
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ]
        ],
        "upsample_rates": [
            8,
            8,
            2,
            2
        ],
        "upsample_initial_channel": 512,
        "upsample_kernel_sizes": [
            16,
            16,
            4,
            4
        ],
        "n_layers_q": 3,
        "use_spectral_norm": false,
        "n_speakers": 0, // number of speakers, while be automatically set if n_speakers is 0 and multi_speaker_training is true
        "gin_channels": 256,
        "use_sdp": true
    },
    "train": {
        "fp16_run": true,
        "learning_rate": 2e-4,
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-9,
        "batch_size": 16,
        "lr_decay": 0.999875,
        // "segment_size": 8192,
        "init_lr_ratio": 1,
        "warmup_epochs": 0,
        "c_mel": 45,
        "c_kl": 1.0,
        "AdamW": {
            "betas": [
                0.8,
                0.99
            ],
            "eps": 1e-9,
        }
    }
}