tokenizer_config.json

{
  "added_tokens_decoder": {
    "4": {
      "content": "by",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "5": {
      "content": "ch",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "6": {
      "content": "cl",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "11": {
      "content": "hy",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "15": {
      "content": "ky",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "19": {
      "content": "py",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "22": {
      "content": "sh",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "23": {
      "content": "ts",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "29": {
      "content": "[UNK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "30": {
      "content": "[PAD]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "31": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "32": {
      "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": "|"
}