tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<s>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "1": {
      "content": "<pad>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "2": {
      "content": "</s>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "3": {
      "content": "<unk>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "4": {
      "content": "|",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "68": {
      "content": "ౄ",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "69": {
      "content": "ఁ",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "70": {
      "content": "ౖ",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "71": {
      "content": ".",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "72": {
      "content": ",",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "73": {
      "content": "0",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "74": {
      "content": "1",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "75": {
      "content": "2",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "76": {
      "content": "3",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "77": {
      "content": "4",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "78": {
      "content": "5",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "79": {
      "content": "6",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "80": {
      "content": "7",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "81": {
      "content": "8",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "82": {
      "content": "9",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "backend": "custom",
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "do_lower_case": false,
  "eos_token": "</s>",
  "is_local": false,
  "local_files_only": false,
  "model_max_length": 1000000000000000019884624838656,
  "model_specific_special_tokens": {
    "word_delimiter_token": "|"
  },
  "pad_token": "<pad>",
  "processor_class": "Wav2Vec2Processor",
  "replace_word_delimiter_char": " ",
  "target_lang": null,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "unk_token": "<unk>",
  "word_delimiter_token": "|"
}