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