N/config.json

{
  "train": {
    "log_interval": 500,
    "eval_interval": 1500,
    "seed": 52,
    "epochs": 10000,
    "learning_rate": 0.0001,
    "betas": [
      0.8,
      0.99
    ],
    "eps": 1e-09,
    "batch_size": 4,
    "fp16_run": false,
    "lr_decay": 0.999875,
    "segment_size": 16384,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0,
    "skip_optimizer": true
  },
  "data": {
    "training_files": "filelists/train.list",
    "validation_files": "filelists/val.list",
    "max_wav_value": 32768.0,
    "sampling_rate": 44100,
    "filter_length": 2048,
    "hop_length": 512,
    "win_length": 2048,
    "n_mel_channels": 128,
    "mel_fmin": 0.0,
    "mel_fmax": null,
    "add_blank": true,
    "n_speakers": 76,
    "cleaned_text": true,
    "spk2id": {
      "AKIMOTO_MANATSU": 0,
      "ENDO_SAKURA": 1,
      "ETO_MISA": 2,
      "FUKAGAWA_MAI": 3,
      "HARUKA_KUROMI": 4,
      "HASHIMOTO_NANAMI": 5,
      "HAYAKAWA_SEIRA": 6,
      "HIGUCHI_HINA": 7,
      "HORI_MIONA": 8,
      "HOSHINO_MINAMI": 9,
      "ICHINOSE_MIKU": 10,
      "IKEDA_TERESA": 11,
      "IKOMA_RINA": 12,
      "IKUTA_ERIKA": 13,
      "INOUE_NAGI": 14,
      "INOUE_SAYURI": 15,
      "IOKI_MAO": 16,
      "ITO_JUNNA": 17,
      "ITO_KARIN": 18,
      "ITO_MARIKA": 19,
      "ITO_RIRIA": 20,
      "IWAMOTO_RENKA": 21,
      "KAKEHASHI_SAYAKA": 22,
      "KAKI_HARUKA": 23,
      "KANAGAWA_SAYA": 24,
      "KAWAGO_HINA": 25,
      "KAWAMURA_MAHIRO": 26,
      "KAWASAKI_SAKURA": 27,
      "KITAGAWA_YURI": 28,
      "KITANO_HINAKO": 29,
      "KUBO_SHIORI": 30,
      "MATSUMURA_SAYURI": 31,
      "MIYU_MATSUO": 32,
      "MUKAI_HAZUKI": 33,
      "NAKADA_KANA": 34,
      "NAKAMOTO_HIMEKA": 35,
      "NAKAMURA_RENO": 36,
      "NAKANISHI_ARUNO": 37,
      "NAO_YUMIKI": 38,
      "NISHINO_NANASE": 39,
      "NOUJO_AMI": 40,
      "OGAWA_AYA": 41,
      "OKAMOTO_HINA": 42,
      "OKUDA_IROHA": 43,
      "OZONO_MOMOKO": 44,
      "RIKA_SATO": 45,
      "RUNA_HAYASHI": 46,
      "SAGARA_IORI": 47,
      "SAITO_ASUKA": 48,
      "SAITO_CHIHARU": 49,
      "SAKAGUCHI_TAMAMI": 50,
      "SAKURAI_REIKA": 51,
      "SASAKI_KOTOKO": 52,
      "SATO_KAEDE": 53,
      "SATO_YUURI": 54,
      "SEIMIYA_REI": 55,
      "SHIBATA_YUNA": 56,
      "SHINUCHI_MAI": 57,
      "SHIRAISHI_MAI": 58,
      "SUGAWARA_SATSUKI": 59,
      "SUZUKI_AYANE": 60,
      "TAKAYAMA_KAZUMI": 61,
      "TAMURA_MAYU": 62,
      "TERADA_RANZE": 63,
      "TOMISATO_NAO": 64,
      "TSUTSUI_AYAME": 65,
      "UMEZAWA_MINAMI": 66,
      "WADA_MAAYA": 67,
      "WAKATSUKI_YUMI": 68,
      "WATANABE_MIRIA": 69,
      "YAKUBO_MIO": 70,
      "YAMASHITA_MIZUKI": 71,
      "YAMAZAKI_RENA": 72,
      "YODA_YUUKI": 73,
      "YOSHIDA_AYANO_CHRISTIE": 74
    }
  },
  "model": {
    "use_spk_conditioned_encoder": true,
    "use_noise_scaled_mas": true,
    "use_mel_posterior_encoder": false,
    "use_duration_discriminator": true,
    "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,
      8,
      2,
      2
    ],
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "gin_channels": 256
  }
}