tokenizer_config.json

{
  "added_tokens_decoder": {
    "35": {
      "content": "[UNK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "36": {
      "content": "[PAD]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "37": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "38": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "additional_special_tokens": [],
  "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",
  "tokenizer_file": null,
  "unk_token": "[UNK]",
  "vocab": {
    "[PAD]": 36,
    "[UNK]": 35,
    "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,
    "r": 17,
    "s": 18,
    "t": 19,
    "u": 20,
    "v": 21,
    "x": 22,
    "z": 23,
    "|": 0,
    "ā": 24,
    "č": 25,
    "ē": 26,
    "ģ": 27,
    "ī": 28,
    "ķ": 29,
    "ļ": 30,
    "ņ": 31,
    "š": 32,
    "ū": 33,
    "ž": 34
  },
  "word_delimiter_token": "|"
}