tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 21,
      "content": "[UNK]",
      "single_word": false,
      "lstrip": true,
      "rstrip": true,
      "normalized": false,
      "special": true
    },
    {
      "id": 33,
      "content": "[PAD]",
      "single_word": false,
      "lstrip": true,
      "rstrip": true,
      "normalized": false,
      "special": true
    },
    {
      "id": 40,
      "content": "<s>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    },
    {
      "id": 41,
      "content": "</s>",
      "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": "CTC",
    "pad_token": "[PAD]",
    "word_delimiter_token": " ",
    "cleanup": true
  },
  "model": {
    "type": "WordLevel",
    "vocab": {
      " ": 22,
      "[PAD]": 33,
      "[UNK]": 21,
      "a": 3,
      "b": 14,
      "d": 19,
      "e": 13,
      "f": 20,
      "h": 30,
      "i": 38,
      "j": 9,
      "k": 1,
      "l": 39,
      "m": 24,
      "n": 29,
      "o": 2,
      "p": 12,
      "s": 8,
      "t": 16,
      "u": 11,
      "v": 17,
      "w": 34,
      "z": 35,
      "æ": 4,
      "ð": 28,
      "ŋ": 7,
      "ɑ": 0,
      "ɔ": 36,
      "ɚ": 32,
      "ɛ": 15,
      "ɡ": 37,
      "ɪ": 18,
      "ɹ": 23,
      "ʃ": 5,
      "ʊ": 10,
      "ʌ": 31,
      "ʒ": 25,
      "ˌ": 26,
      "͡": 6,
      "θ": 27,
      "</s>": 41,
      "<s>": 40
    },
    "unk_token": "[UNK]"
  }
}