Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 39
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "pad_token": "ا",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "ا",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "39": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "ara",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "ا",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

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