French/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,
      "m": 4,
      "a": 5,
      "ɑ̃": 6,
      "d": 7,
      "ɔ": 8,
      "n": 9,
      "b": 10,
      "ʁ": 11,
      "ə": 12,
      "ɡ": 13,
      "ʒ": 14,
      "i": 15,
      "v": 16,
      "t": 17,
      "k": 18,
      "o": 19,
      "ɛ̃": 20,
      "w": 21,
      "y": 22,
      "j": 23,
      "e": 24,
      "ɔ̃": 25,
      "p": 26,
      "ɛ": 27,
      "f": 28,
      "s": 29,
      "z": 30,
      "l": 31,
      "u": 32,
      "ʃ": 33,
      "œ": 34,
      "ø": 35,
      "ɲ": 36,
      "t̠ʃ": 37,
      "d̠ʒ": 38
    },
    "unk_token": "UNK"
  }
}