tokenizer_config.json

{
  "added_tokens_decoder": {
    "27": {
      "content": "[UNK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "28": {
      "content": "[PAD]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "29": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "do_lower_case": false,
  "eos_token": "</s>",
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "[PAD]",
  "replace_word_delimiter_char": " ",
  "target_lang": null,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "unk_token": "[UNK]",
  "vocab_dict": {
    "[PAD]": 28,
    "[UNK]": 27,
    "a": 1,
    "b": 2,
    "c": 3,
    "d": 4,
    "e": 5,
    "f": 6,
    "g": 7,
    "h": 8,
    "i": 9,
    "j": 10,
    "k": 11,
    "l": 12,
    "m": 13,
    "n": 14,
    "o": 15,
    "p": 16,
    "q": 17,
    "r": 18,
    "s": 19,
    "t": 20,
    "u": 21,
    "v": 22,
    "w": 23,
    "x": 24,
    "y": 25,
    "z": 26,
    "|": 0
  },
  "word_delimiter_token": "|"
}