config.json

{
  "model_type": "melotts",
  "sampling_rate": 44100,
  "filter_length": 2048,
  "hop_length": 512,
  "add_blank": true,
  "n_speakers": 1,
  "spk2id": {
    "EN-Newest": 0
  },
  "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,
  "n_layers_trans_flow": 3,
  "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,
  "num_tones": 16,
  "num_languages": 8,
  "n_vocab": 219,
  "symbols": [
    "_",
    "\"",
    "(",
    ")",
    "*",
    "/",
    ":",
    "AA",
    "E",
    "EE",
    "En",
    "N",
    "OO",
    "Q",
    "V",
    "[",
    "\\",
    "]",
    "^",
    "a",
    "a:",
    "aa",
    "ae",
    "ah",
    "ai",
    "an",
    "ang",
    "ao",
    "aw",
    "ay",
    "b",
    "by",
    "c",
    "ch",
    "d",
    "dh",
    "dy",
    "e",
    "e:",
    "eh",
    "ei",
    "en",
    "eng",
    "er",
    "ey",
    "f",
    "g",
    "gy",
    "h",
    "hh",
    "hy",
    "i",
    "i0",
    "i:",
    "ia",
    "ian",
    "iang",
    "iao",
    "ie",
    "ih",
    "in",
    "ing",
    "iong",
    "ir",
    "iu",
    "iy",
    "j",
    "jh",
    "k",
    "ky",
    "l",
    "m",
    "my",
    "n",
    "ng",
    "ny",
    "o",
    "o:",
    "ong",
    "ou",
    "ow",
    "oy",
    "p",
    "py",
    "q",
    "r",
    "ry",
    "s",
    "sh",
    "t",
    "th",
    "ts",
    "ty",
    "u",
    "u:",
    "ua",
    "uai",
    "uan",
    "uang",
    "uh",
    "ui",
    "un",
    "uo",
    "uw",
    "v",
    "van",
    "ve",
    "vn",
    "w",
    "x",
    "y",
    "z",
    "zh",
    "zy",
    "~",
    "\u00e6",
    "\u00e7",
    "\u00f0",
    "\u00f8",
    "\u014b",
    "\u0153",
    "\u0250",
    "\u0251",
    "\u0252",
    "\u0254",
    "\u0255",
    "\u0259",
    "\u025b",
    "\u025c",
    "\u0261",
    "\u0263",
    "\u0265",
    "\u0266",
    "\u026a",
    "\u026b",
    "\u026c",
    "\u026d",
    "\u026f",
    "\u0272",
    "\u0275",
    "\u0278",
    "\u0279",
    "\u027e",
    "\u0281",
    "\u0283",
    "\u028a",
    "\u028c",
    "\u028e",
    "\u028f",
    "\u0291",
    "\u0292",
    "\u029d",
    "\u02b2",
    "\u02c8",
    "\u02cc",
    "\u02d0",
    "\u0303",
    "\u0329",
    "\u03b2",
    "\u03b8",
    "\u1100",
    "\u1101",
    "\u1102",
    "\u1103",
    "\u1104",
    "\u1105",
    "\u1106",
    "\u1107",
    "\u1108",
    "\u1109",
    "\u110a",
    "\u110b",
    "\u110c",
    "\u110d",
    "\u110e",
    "\u110f",
    "\u1110",
    "\u1111",
    "\u1112",
    "\u1161",
    "\u1162",
    "\u1163",
    "\u1164",
    "\u1165",
    "\u1166",
    "\u1167",
    "\u1168",
    "\u1169",
    "\u116a",
    "\u116b",
    "\u116c",
    "\u116d",
    "\u116e",
    "\u116f",
    "\u1170",
    "\u1171",
    "\u1172",
    "\u1173",
    "\u1174",
    "\u1175",
    "\u11a8",
    "\u11ab",
    "\u11ae",
    "\u11af",
    "\u11b7",
    "\u11b8",
    "\u11bc",
    "\u3138",
    "!",
    "?",
    "\u2026",
    ",",
    ".",
    "'",
    "-",
    "\u00bf",
    "\u00a1",
    "SP",
    "UNK"
  ]
}