phoneme_tokenizer/tokenizer.json

{
  "version": "1.0",
  "truncation": null,
  "padding": null,
  "added_tokens": [
    {
      "id": 0,
      "content": "<blank>",
      "single_word": false,
      "lstrip": false,
      "rstrip": false,
      "normalized": false,
      "special": true
    }
  ],
  "normalizer": null,
  "pre_tokenizer": {
    "type": "WhitespaceSplit"
  },
  "post_processor": {
    "type": "TemplateProcessing",
    "single": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      }
    ],
    "pair": [
      {
        "Sequence": {
          "id": "A",
          "type_id": 0
        }
      },
      {
        "Sequence": {
          "id": "B",
          "type_id": 1
        }
      }
    ],
    "special_tokens": {}
  },
  "decoder": null,
  "model": {
    "type": "WordLevel",
    "vocab": {
      "<blank>": 0,
      "A": 1,
      "E": 2,
      "I": 3,
      "N": 4,
      "O": 5,
      "U": 6,
      "a": 7,
      "b": 8,
      "by": 9,
      "ch": 10,
      "cl": 11,
      "d": 12,
      "dy": 13,
      "e": 14,
      "f": 15,
      "g": 16,
      "gy": 17,
      "h": 18,
      "hy": 19,
      "i": 20,
      "j": 21,
      "k": 22,
      "ky": 23,
      "m": 24,
      "my": 25,
      "n": 26,
      "ny": 27,
      "o": 28,
      "p": 29,
      "py": 30,
      "r": 31,
      "ry": 32,
      "s": 33,
      "sh": 34,
      "t": 35,
      "ts": 36,
      "ty": 37,
      "u": 38,
      "v": 39,
      "w": 40,
      "y": 41,
      "z": 42,
      "pau": 43
    },
    "unk_token": "<blank>"
  }
}