Upload tokenizer

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 +1,14 @@
+{
+  "bos_token": "<s>",
+  "cache_dir": "/tmp/",
+  "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 +1,89 @@
+{
+  "ara": {
+    "%": 1,
+    "0": 2,
+    "1": 3,
+    "2": 4,
+    "3": 5,
+    "4": 6,
+    "5": 7,
+    "6": 8,
+    "7": 9,
+    "8": 10,
+    "9": 11,
+    "@": 12,
+    "[PAD]": 84,
+    "[UNK]": 83,
+    "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,
+    "q": 29,
+    "r": 30,
+    "s": 31,
+    "t": 32,
+    "u": 33,
+    "v": 34,
+    "w": 35,
+    "x": 36,
+    "y": 37,
+    "z": 38,
+    "|": 0,
+    "é": 39,
+    "̇": 40,
+    "ء": 41,
+    "آ": 42,
+    "أ": 43,
+    "ؤ": 44,
+    "إ": 45,
+    "ئ": 46,
+    "ا": 47,
+    "ب": 48,
+    "ة": 49,
+    "ت": 50,
+    "ث": 51,
+    "ج": 52,
+    "ح": 53,
+    "خ": 54,
+    "د": 55,
+    "ذ": 56,
+    "ر": 57,
+    "ز": 58,
+    "س": 59,
+    "ش": 60,
+    "ص": 61,
+    "ض": 62,
+    "ط": 63,
+    "ظ": 64,
+    "ع": 65,
+    "غ": 66,
+    "ـ": 67,
+    "ف": 68,
+    "ق": 69,
+    "ك": 70,
+    "ل": 71,
+    "م": 72,
+    "ن": 73,
+    "ه": 74,
+    "و": 75,
+    "ى": 76,
+    "ي": 77,
+    "ﺇ": 78,
+    "ﻵ": 79,
+    "ﻷ": 80,
+    "ﻹ": 81,
+    "ﻻ": 82
+  }
+}