tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "<pad>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "1": {
      "content": "<s>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "</s>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "<unk>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "57": {
      "content": "[UNK]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "58": {
      "content": "[PAD]",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    }
  },
  "bos_token": "<s>",
  "clean_up_tokenization_spaces": true,
  "do_lower_case": false,
  "do_normalize": true,
  "eos_token": "</s>",
  "model_max_length": 9223372036854775807,
  "pad_token": "[PAD]",
  "processor_class": "Wav2Vec2Processor",
  "replace_word_delimiter_char": " ",
  "return_attention_mask": false,
  "target_lang": "ara-aeb",
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "unk_token": "[UNK]",
  "word_delimiter_token": "|"
}