Upload tokenizer

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<unk>": 58
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_blank": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "د",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "urd-script_arabic",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "د",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>",
+  "verbose": false
+}

vocab.json

@@ -0,0 +1,60 @@
+{
+  " ": 26,
+  "'": 4,
+  "0": 48,
+  "1": 36,
+  "2": 24,
+  "3": 20,
+  "4": 35,
+  "5": 8,
+  "6": 51,
+  "7": 27,
+  "8": 7,
+  "9": 23,
+  "_": 30,
+  "آ": 2,
+  "أ": 12,
+  "ؤ": 3,
+  "ئ": 25,
+  "ا": 15,
+  "ب": 31,
+  "ت": 28,
+  "ث": 16,
+  "ج": 49,
+  "ح": 54,
+  "خ": 1,
+  "د": 0,
+  "ذ": 47,
+  "ر": 22,
+  "ز": 44,
+  "س": 57,
+  "ش": 34,
+  "ص": 19,
+  "ض": 42,
+  "ط": 6,
+  "ظ": 32,
+  "ع": 38,
+  "غ": 37,
+  "ف": 29,
+  "ق": 17,
+  "ل": 13,
+  "م": 40,
+  "ن": 9,
+  "و": 10,
+  "ٰ": 39,
+  "ٹ": 46,
+  "پ": 52,
+  "چ": 5,
+  "ڈ": 55,
+  "ڑ": 21,
+  "ژ": 43,
+  "ک": 45,
+  "گ": 14,
+  "ں": 56,
+  "ھ": 41,
+  "ہ": 53,
+  "ۂ": 50,
+  "ی": 18,
+  "ے": 11,
+  "—": 33
+}