tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 3,
      "content": "<unk>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "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
    }
  ],
  "normalizer": {
    "type": "Sequence",
    "normalizers": [
      {
        "type": "Replace",
        "pattern": {
          "String": "\\s+"
        },
        "content": "|"
      }
    ]
  },
  "pre_tokenizer": {
    "type": "Split",
    "pattern": {
      "String": "\\S"
    },
    "behavior": "Isolated",
    "invert": false
  },
  "post_processor": null,
  "decoder": {
    "type": "CTC",
    "pad_token": "<pad>",
    "word_delimiter_token": "|",
    "cleanup": true
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<pad>": 0,
      "<s>": 1,
      "</s>": 2,
      "<unk>": 3,
      "a": 4,
      "b": 5,
      "d": 6,
      "e": 7,
      "f": 8,
      "h": 9,
      "i": 10,
      "j": 11,
      "k": 12,
      "l": 13,
      "m": 14,
      "n": 15,
      "o": 16,
      "p": 17,
      "s": 18,
      "t": 19,
      "u": 20,
      "v": 21,
      "w": 22,
      "z": 23,
      "æ": 24,
      "ð": 25,
      "ŋ": 26,
      "ɑ": 27,
      "ɔ": 28,
      "ə": 29,
      "ɛ": 30,
      "ɡ": 31,
      "ɪ": 32,
      "ɹ": 33,
      "ɾ": 34,
      "ʃ": 35,
      "ʊ": 36,
      "ʌ": 37,
      "ʒ": 38,
      "ʔ": 39,
      "θ": 40
    },
    "unk_token": "<unk>"
  }
}