configs/58v1.json

{
    "train": {
        "log_interval": 400,
        "eval_interval": 800,
        "seed": 1234,
        "epochs": 10000,
        "learning_rate": 0.0002,
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-09,
        "batch_size": 16,
        "fp16_run": false,
        "half_type": "fp16",
        "lr_decay": 0.999875,
        "segment_size": 10240,
        "init_lr_ratio": 1,
        "warmup_epochs": 0,
        "c_mel": 45,
        "c_kl": 1.0,
        "use_sr": true,
        "max_speclen": 512,
        "port": "8001",
        "keep_ckpts": 50,
        "all_in_mem": false,
        "vol_aug": true
    },
    "data": {
        "training_files": "filelists/train.txt",
        "validation_files": "filelists/val.txt",
        "max_wav_value": 32768.0,
        "sampling_rate": 44100,
        "filter_length": 2048,
        "hop_length": 512,
        "win_length": 2048,
        "n_mel_channels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": 22050,
        "unit_interpolate_mode": "nearest"
    },
    "model": {
        "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,
            2
        ],
        "upsample_initial_channel": 512,
        "upsample_kernel_sizes": [
            16,
            16,
            4,
            4,
            4
        ],
        "n_layers_q": 3,
        "n_flow_layer": 4,
        "use_spectral_norm": false,
        "gin_channels": 768,
        "ssl_dim": 768,
        "n_speakers": 58,
        "vocoder_name": "nsf-hifigan",
        "speech_encoder": "vec768l12",
        "speaker_embedding": false,
        "vol_embedding": true,
        "use_depthwise_conv": false,
        "flow_share_parameter": false,
        "use_automatic_f0_prediction": true
    },
    "spk": {
        "AKIMOTO_MANATSU": 0,
        "ENDO_SAKURA": 1,
        "ETO_MISA": 2,
        "FUKAGAWA_MAI": 3,
        "HARUKA_KUROMI": 4,
        "HASHIMOTO_NANAMI": 5,
        "HAYAKAWA_SEIRA": 6,
        "HORI_MIONA": 7,
        "HOSHINO_MINAMI": 8,
        "ICHINOSE_MIKU": 9,
        "IKEDA_TERESA": 10,
        "IKUTA_ERIKA": 11,
        "INOUE_NAGI": 12,
        "INOUE_SAYURI": 13,
        "IOKI_MAO": 14,
        "ITO_RIRIA": 15,
        "IWAMOTO_RENKA": 16,
        "KAKEHASHI_SAYAKA": 17,
        "KAKI_HARUKA": 18,
        "KANAGAWA_SAYA": 19,
        "KAWASAKI_SAKURA": 20,
        "KITAGAWA_YURI": 21,
        "KITANO_HINAKO": 22,
        "KUBO_SHIORI": 23,
        "MATSUMURA_SAYURI": 24,
        "MIYU_MATSUO": 25,
        "MUKAI_HAZUKI": 26,
        "NAKAMOTO_HIMEKA": 27,
        "NAKANISHI_ARUNO": 28,
        "NAO_YUMIKI": 29,
        "NISHINO_NANASE": 30,
        "OGAWA_AYA": 31,
        "OKAMOTO_HINA": 32,
        "OKUDA_IROHA": 33,
        "OZONO_MOMOKO": 34,
        "RIKA_SATO": 35,
        "RUNA_HAYASHI": 36,
        "SAITO_ASUKA": 37,
        "SAKAGUCHI_TAMAMI": 38,
        "SAKURAI_REIKA": 39,
        "SASAKI_KOTOKO": 40,
        "SATO_KAEDE": 41,
        "SATO_YUURI": 42,
        "SEIMIYA_REI": 43,
        "SHIBATA_YUNA": 44,
        "SHINUCHI_MAI": 45,
        "SHIRAISHI_MAI": 46,
        "SUGAWARA_SATSUKI": 47,
        "SUZUKI_AYANE": 48,
        "TAKAYAMA_KAZUMI": 49,
        "TAMURA_MAYU": 50,
        "TERADA_RANZE": 51,
        "TOMISATO_NAO": 52,
        "TSUTSUI_AYAME": 53,
        "UMEZAWA_MINAMI": 54,
        "YAKUBO_MIO": 55,
        "YAMASHITA_MIZUKI": 56,
        "YODA_YUUKI": 57
    }
}