Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 35,
-  "<s>": 34
+  "</s>": 51,
+  "<s>": 50
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "32": {
+    "48": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "33": {
+    "49": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "34": {
+    "50": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "35": {
+    "51": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,38 +1,54 @@
 {
   "kur": {
-    "[PAD]": 33,
-    "[UNK]": 32,
+    "[PAD]": 49,
+    "[UNK]": 48,
     "_": 1,
-    "a": 2,
-    "b": 3,
-    "c": 4,
-    "d": 5,
-    "e": 6,
-    "f": 7,
-    "g": 8,
-    "h": 9,
-    "i": 10,
-    "j": 11,
-    "k": 12,
-    "l": 13,
-    "m": 14,
-    "n": 15,
-    "o": 16,
-    "p": 17,
-    "q": 18,
-    "r": 19,
-    "s": 20,
-    "t": 21,
-    "v": 22,
-    "y": 23,
-    "z": 24,
     "|": 0,
-    "«": 25,
-    "»": 26,
-    "،": 27,
-    "أ": 28,
-    "ـ": 29,
-    "ّ": 30,
-    "ﮔ": 31
+    "«": 2,
+    "»": 3,
+    "،": 4,
+    "أ": 5,
+    "ؤ": 6,
+    "ئ": 7,
+    "ا": 8,
+    "ب": 9,
+    "ت": 10,
+    "ث": 11,
+    "ج": 12,
+    "ح": 13,
+    "خ": 14,
+    "د": 15,
+    "ر": 16,
+    "ز": 17,
+    "س": 18,
+    "ش": 19,
+    "ع": 20,
+    "غ": 21,
+    "ـ": 22,
+    "ف": 23,
+    "ق": 24,
+    "ك": 25,
+    "ل": 26,
+    "م": 27,
+    "ن": 28,
+    "ه": 29,
+    "و": 30,
+    "ى": 31,
+    "ي": 32,
+    "ّ": 33,
+    "پ": 34,
+    "چ": 35,
+    "ڕ": 36,
+    "ژ": 37,
+    "ڤ": 38,
+    "ک": 39,
+    "گ": 40,
+    "ڵ": 41,
+    "ھ": 42,
+    "ۆ": 43,
+    "ی": 44,
+    "ێ": 45,
+    "ە": 46,
+    "ﮔ": 47
   }
 }