tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<PAD>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "1": {
      "content": "<UNK>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "2": {
      "content": "<BOS>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "3": {
      "content": "<EOS>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "5": {
      "content": "AA",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "6": {
      "content": "AE",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "7": {
      "content": "AH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "8": {
      "content": "AW",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "9": {
      "content": "AY",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "11": {
      "content": "CH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "13": {
      "content": "DH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "14": {
      "content": "DX",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "15": {
      "content": "EH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "16": {
      "content": "ER",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "17": {
      "content": "EY",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "20": {
      "content": "HH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "21": {
      "content": "IH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "22": {
      "content": "IY",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "23": {
      "content": "JH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "28": {
      "content": "NG",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "29": {
      "content": "OW",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "30": {
      "content": "OY",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "34": {
      "content": "SH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "36": {
      "content": "TH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "37": {
      "content": "UH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "38": {
      "content": "UW",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "43": {
      "content": "ZH",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "44": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "45": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "</s>",
  "extra_special_tokens": {},
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "<PAD>",
  "processor_class": "Wav2Vec2Processor",
  "replace_word_delimiter_char": " ",
  "target_lang": null,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "unk_token": "<UNK>",
  "word_delimiter_token": "|"
}