tokenizer_config.json

{
  "added_tokens_decoder": {
    "1": {
      "content": "m̩",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "3": {
      "content": "aɪ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "5": {
      "content": "nOIsE",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "8": {
      "content": "ẽɪ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "9": {
      "content": "ɔ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "12": {
      "content": "eɪ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "14": {
      "content": "ɹ̩̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "16": {
      "content": "n̩",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "17": {
      "content": "ɪ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "18": {
      "content": "ãɪ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "26": {
      "content": "l̩",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "27": {
      "content": "æ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "28": {
      "content": "{E_tɹAns}",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "29": {
      "content": "oʊ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "30": {
      "content": "aʊ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "31": {
      "content": "dʒ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "36": {
      "content": "ɔ̃ɪ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "39": {
      "content": "ʊ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "41": {
      "content": "tʃ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "44": {
      "content": "ɛ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "46": {
      "content": "ɑ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "48": {
      "content": "õʊ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "49": {
      "content": "ɹ̩",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "53": {
      "content": "ʌ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "54": {
      "content": "ɾ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "55": {
      "content": "ãʊ̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "57": {
      "content": "ə̃",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "63": {
      "content": "ɔɪ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "65": {
      "content": "[UNK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "66": {
      "content": "[PAD]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "67": {
      "content": "<s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "68": {
      "content": "</s>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    }
  },
  "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",
  "unk_token": "[UNK]",
  "word_delimiter_token": "|"
}