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 +1,50 @@
+{
+  "ara": {
+    "#": 1,
+    "*": 2,
+    ".": 3,
+    "@": 4,
+    "[PAD]": 45,
+    "[UNK]": 44,
+    "_": 5,
+    "|": 0,
+    "؟": 6,
+    "ء": 7,
+    "آ": 8,
+    "أ": 9,
+    "ؤ": 10,
+    "إ": 11,
+    "ئ": 12,
+    "ا": 13,
+    "ب": 14,
+    "ة": 15,
+    "ت": 16,
+    "ث": 17,
+    "ج": 18,
+    "ح": 19,
+    "خ": 20,
+    "د": 21,
+    "ذ": 22,
+    "ر": 23,
+    "ز": 24,
+    "س": 25,
+    "ش": 26,
+    "ص": 27,
+    "ض": 28,
+    "ط": 29,
+    "ظ": 30,
+    "ع": 31,
+    "غ": 32,
+    "ف": 33,
+    "ق": 34,
+    "ك": 35,
+    "ل": 36,
+    "م": 37,
+    "ن": 38,
+    "ه": 39,
+    "و": 40,
+    "ى": 41,
+    "ي": 42,
+    "ّ": 43
+  }
+}