Upload tokenizer

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 117,
+  "<s>": 116
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "114": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "117": {
+      "content": "</s>",
+      "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": "ara",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,120 @@
+{
+  "ara": {
+    "\t": 0,
+    "!": 2,
+    "'": 3,
+    ",": 4,
+    "-": 5,
+    ".": 6,
+    "0": 7,
+    "3": 8,
+    "4": 9,
+    "=": 10,
+    ">": 11,
+    "?": 12,
+    "A": 13,
+    "B": 14,
+    "C": 15,
+    "D": 16,
+    "E": 17,
+    "F": 18,
+    "G": 19,
+    "H": 20,
+    "I": 21,
+    "J": 22,
+    "K": 23,
+    "L": 24,
+    "M": 25,
+    "N": 26,
+    "O": 27,
+    "P": 28,
+    "R": 29,
+    "S": 30,
+    "T": 31,
+    "U": 32,
+    "V": 33,
+    "W": 34,
+    "X": 35,
+    "Y": 36,
+    "Z": 37,
+    "[": 38,
+    "[PAD]": 115,
+    "[UNK]": 114,
+    "]": 39,
+    "a": 40,
+    "b": 41,
+    "c": 42,
+    "d": 43,
+    "e": 44,
+    "f": 45,
+    "g": 46,
+    "h": 47,
+    "i": 48,
+    "j": 49,
+    "k": 50,
+    "l": 51,
+    "m": 52,
+    "n": 53,
+    "o": 54,
+    "p": 55,
+    "q": 56,
+    "r": 57,
+    "s": 58,
+    "t": 59,
+    "u": 60,
+    "v": 61,
+    "w": 62,
+    "x": 63,
+    "y": 64,
+    "z": 65,
+    "|": 1,
+    "،": 66,
+    "؛": 67,
+    "؟": 68,
+    "ء": 69,
+    "آ": 70,
+    "أ": 71,
+    "ؤ": 72,
+    "إ": 73,
+    "ئ": 74,
+    "ا": 75,
+    "ب": 76,
+    "ة": 77,
+    "ت": 78,
+    "ث": 79,
+    "ج": 80,
+    "ح": 81,
+    "خ": 82,
+    "د": 83,
+    "ذ": 84,
+    "ر": 85,
+    "ز": 86,
+    "س": 87,
+    "ش": 88,
+    "ص": 89,
+    "ض": 90,
+    "ط": 91,
+    "ظ": 92,
+    "ع": 93,
+    "غ": 94,
+    "ف": 95,
+    "ق": 96,
+    "ك": 97,
+    "ل": 98,
+    "م": 99,
+    "ن": 100,
+    "ه": 101,
+    "و": 102,
+    "ى": 103,
+    "ي": 104,
+    "ً": 105,
+    "ٍ": 106,
+    "َ": 107,
+    "ُ": 108,
+    "ِ": 109,
+    "ّ": 110,
+    "ی": 111,
+    "–": 112,
+    "’": 113
+  }
+}