tokenizer_config.json

{
  "added_tokens_decoder": {
    "1": {
      "content": "</s>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "2": {
      "content": "<pad>",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "3": {
      "content": "لِلَّهِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "4": {
      "content": "الْحَمْدُ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "5": {
      "content": "الدِّينِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "6": {
      "content": "الْمَغْضُوبِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "7": {
      "content": "نَعْبُدُ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "8": {
      "content": "اللَّهِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "9": {
      "content": "الصِّرَاطَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "10": {
      "content": "الرَّحْمَٰنِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "11": {
      "content": "اهْدِنَا",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "12": {
      "content": "يَوْمِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "13": {
      "content": "الَّذِينَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "14": {
      "content": "الْعَالَمِينَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "15": {
      "content": "الضَّالِّينَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "16": {
      "content": "غَيْرِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "17": {
      "content": "صِرَاطَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "18": {
      "content": "أَنْعَمْتَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "19": {
      "content": "عَلَيْهِمْ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "20": {
      "content": "بِسْمِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "21": {
      "content": "وَلَا",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "22": {
      "content": "مَالِكِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "23": {
      "content": "وَإِيَّاكَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "24": {
      "content": "إِيَّاكَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "25": {
      "content": "نَسْتَعِينُ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "26": {
      "content": "الْمُسْتَقِيمَ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "27": {
      "content": "الرَّحِيمِ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "28": {
      "content": "رَبِّ",
      "lstrip": true,
      "normalized": false,
      "rstrip": true,
      "single_word": false,
      "special": false
    },
    "29": {
      "content": "<s>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "30": {
      "content": "<unk>",
      "lstrip": false,
      "normalized": true,
      "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>",
  "processor_class": "Wav2Vec2Processor",
  "replace_word_delimiter_char": " ",
  "target_lang": null,
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
  "unk_token": "<unk>",
  "word_delimiter_token": "|"
}