tokenizer_config.json

{
  "added_tokens_decoder": {
    "0": {
      "content": "[PAD]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "1": {
      "content": "[UNK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "2": {
      "content": "[CLS]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "3": {
      "content": "[SEP]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "4": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "5": {
      "content": "[رابط]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "6": {
      "content": "[بريد]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    },
    "7": {
      "content": "[مستخدم]",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": true,
      "special": true
    }
  },
  "clean_up_tokenization_spaces": false,
  "cls_token": "[CLS]",
  "do_basic_tokenize": true,
  "do_lower_case": false,
  "mask_token": "[MASK]",
  "max_len": 512,
  "model_max_length": 512,
  "never_split": [
    "[بريد]",
    "[مستخدم]",
    "[رابط]"
  ],
  "pad_token": "[PAD]",
  "processor_class": "SpeechT5Processor",
  "sep_token": "[SEP]",
  "strip_accents": null,
  "tokenize_chinese_chars": true,
  "tokenizer_class": "BertTokenizer",
  "unk_token": "[UNK]"
}