tokenizer.json

{
  "char_to_id": {
    "[PAD]": 0,
    "[UNK]": 1,
    "[BOS]": 2,
    "[EOS]": 3,
    "[MASK]": 4,
    " ": 5,
    "ا": 6,
    "ل": 7,
    "ي": 8,
    "م": 9,
    "و": 10,
    "ن": 11,
    "ه": 12,
    "ب": 13,
    "ر": 14,
    "ع": 15,
    "ف": 16,
    "أ": 17,
    "ق": 18,
    "ت": 19,
    "د": 20,
    "ك": 21,
    "ح": 22,
    "ة": 23,
    "س": 24,
    "ج": 25,
    "إ": 26,
    "ص": 27,
    "ذ": 28,
    "ى": 29,
    "خ": 30,
    "ش": 31,
    "ث": 32,
    "ض": 33,
    "ط": 34,
    "ز": 35,
    ":": 36,
    "غ": 37,
    "ء": 38,
    "ئ": 39,
    "ظ": 40,
    "؛": 41,
    "آ": 42,
    "-": 43,
    "ؤ": 44,
    ",": 45,
    "ٰ": 46,
    "ۚ": 47,
    "ۖ": 48,
    "ۗ": 49
  },
  "vocab_size": 50,
  "special_tokens": {
    "PAD": 0,
    "UNK": 1,
    "BOS": 2,
    "EOS": 3,
    "MASK": 4,
    "SPACE": 5
  },
  "diacritic_classes": [
    "NO_DIACRITIC",
    "FATHA",
    "FATHATAN",
    "DAMMA",
    "DAMMATAN",
    "KASRA",
    "KASRATAN",
    "SUKUN",
    "SHADDA",
    "SHADDA_FATHA",
    "SHADDA_FATHATAN",
    "SHADDA_DAMMA",
    "SHADDA_DAMMATAN",
    "SHADDA_KASRA",
    "SHADDA_KASRATAN"
  ],
  "num_labels": 15
}