tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<pad>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "</s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "Regex": ""
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": {
    "type": "Fuse"
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "-": 4,
      "ം": 5,
      "ഃ": 6,
      "അ": 7,
      "ആ": 8,
      "ഇ": 9,
      "ഈ": 10,
      "ഉ": 11,
      "ഊ": 12,
      "ഋ": 13,
      "ഌ": 14,
      "എ": 15,
      "ഏ": 16,
      "ഐ": 17,
      "ഒ": 18,
      "ഓ": 19,
      "ഔ": 20,
      "ക": 21,
      "ഖ": 22,
      "ഗ": 23,
      "ഘ": 24,
      "ങ": 25,
      "ച": 26,
      "ഛ": 27,
      "ജ": 28,
      "ഝ": 29,
      "ഞ": 30,
      "ട": 31,
      "ഠ": 32,
      "ഡ": 33,
      "ഢ": 34,
      "ണ": 35,
      "ത": 36,
      "ഥ": 37,
      "ദ": 38,
      "ധ": 39,
      "ന": 40,
      "പ": 41,
      "ഫ": 42,
      "ബ": 43,
      "ഭ": 44,
      "മ": 45,
      "യ": 46,
      "ര": 47,
      "റ": 48,
      "ല": 49,
      "ള": 50,
      "ഴ": 51,
      "വ": 52,
      "ശ": 53,
      "ഷ": 54,
      "സ": 55,
      "ഹ": 56,
      "ാ": 57,
      "ി": 58,
      "ീ": 59,
      "ു": 60,
      "ൂ": 61,
      "ൃ": 62,
      "ൄ": 63,
      "െ": 64,
      "േ": 65,
      "ൈ": 66,
      "ൊ": 67,
      "ോ": 68,
      "ൌ": 69,
      "്": 70,
      "ൗ": 71,
      "ൠ": 72,
      "ൡ": 73,
      "ൢ": 74,
      "ൣ": 75,
      "൦": 76,
      "൧": 77,
      "൨": 78,
      "൩": 79,
      "൪": 80,
      "൫": 81,
      "൬": 82,
      "൭": 83,
      "൮": 84,
      "൯": 85,
      "൰": 86,
      "൱": 87,
      "൲": 88,
      "൳": 89,
      "൴": 90,
      "൵": 91,
      "൹": 92,
      "ൺ": 93,
      "ൻ": 94,
      "ർ": 95,
      "ൽ": 96,
      "ൾ": 97,
      "ൿ": 98
    },
    "unk_token": "<unk>"
  }
}