Irish/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "UNK",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 1,
      "content": "PAD",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 2,
      "content": "WORD_BOUNDARY",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 3,
      "content": "UTT_BOUNDARY",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Strip",
        "strip_left": true,
        "strip_right": true
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Whitespace"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "SpecialToken": {
          "id": "UTT_BOUNDARY",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {
      "UTT_BOUNDARY": {
        "id": "UTT_BOUNDARY",
        "ids": [
          3
        ],
        "tokens": [
          "UTT_BOUNDARY"
        ]
      }
    }
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "UNK": 0,
      "PAD": 1,
      "WORD_BOUNDARY": 2,
      "UTT_BOUNDARY": 3,
      "kʰ": 4,
      "a": 5,
      "ɾ̪ʲ": 6,
      "d̪ˠ": 7,
      "eː": 8,
      "ʃ": 9,
      "ɪ": 10,
      "n̪ˠ": 11,
      "ə": 12,
      "w": 13,
      "l̪ˠ": 14,
      "ɛ̝": 15,
      "ɡ": 16,
      "ɾ̪ˠ": 17,
      "mˠ": 18,
      "x": 19,
      "iː": 20,
      "sˠ": 21,
      "bˠ": 22,
      "pˠʰ": 23,
      "t̪ʲʰ": 24,
      "ɔ̝": 25,
      "cʰ": 26,
      "t̪ˠʰ": 27,
      "h": 28,
      "vˠ": 29,
      "ʊ": 30,
      "j": 31,
      "oː": 32,
      "ɑː": 33,
      "fˠ": 34,
      "d̠ʒ": 35,
      "l̪ʲ": 36,
      "iːə": 37,
      "uːe": 38,
      "uː": 39,
      "n̪ʲ": 40,
      "d̪ʲ": 41,
      "ɐ": 42,
      "mʲ": 43,
      "pʲʰ": 44,
      "ɣ": 45,
      "ɐɪ": 46,
      "ŋ": 47,
      "i̞": 48,
      "ç": 49,
      "z": 50,
      "fʲ": 51,
      "ʒ": 52,
      "bʲ": 53
    },
    "unk_token": "UNK"
  }
}