tokenizer_config.json

{
  "added_tokens_decoder": {
    "40": {
      "content": "<S>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "41": {
      "content": "</S>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "42": {
      "content": "SIL",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "bos_token": "<S>",
  "clean_up_tokenization_spaces": false,
  "do_phonemize": true,
  "eos_token": "</S>",
  "extra_special_tokens": {},
  "model_max_length": 1000000000000000019884624838656,
  "pad_token": "SIL",
  "phone_delimiter_token": " ",
  "phonemizer_backend": "espeak",
  "phonemizer_lang": "en-us",
  "target_lang": "en-US",
  "tokenizer_class": "Wav2Vec2PhonemeCTCTokenizer",
  "unk_token": "SIL",
  "word_delimiter_token": "SIL"
}