tokenizer_config.json

{
  "added_tokens_decoder": {
    "8": {
      "content": "mw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "12": {
      "content": "nk",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "13": {
      "content": "zw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "16": {
      "content": "nhw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "19": {
      "content": "nkw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "22": {
      "content": "nw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "26": {
      "content": "ndw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "28": {
      "content": "ty",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "30": {
      "content": "nh",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "33": {
      "content": "gy",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "36": {
      "content": "ky",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "37": {
      "content": "mp",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "40": {
      "content": "dh",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "44": {
      "content": "gh",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "50": {
      "content": "by",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "51": {
      "content": "th",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "54": {
      "content": "mb",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "55": {
      "content": "nf",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "60": {
      "content": "tw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "64": {
      "content": "gw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "65": {
      "content": "bw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "66": {
      "content": "zy",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "72": {
      "content": "ng",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "73": {
      "content": "nd",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "76": {
      "content": "sy",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "78": {
      "content": "kw",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "79": {
      "content": "...",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "80": {
      "content": "[UNK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "81": {
      "content": "[PAD]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "82": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "83": {
      "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]",
  "replace_word_delimiter_char": " ",
  "target_lang": "lke",
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "unk_token": "[UNK]",
  "word_delimiter_token": "|"
}