Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 90,
-  "<s>": 89
+  "</s>": 38,
+  "<s>": 37
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "87": {
+    "35": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "88": {
+    "36": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "89": {
+    "37": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "90": {
+    "38": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,

vocab.json

@@ -1,93 +1,41 @@
 {
   "tur": {
-    "[PAD]": 88,
-    "[UNK]": 87,
+    "[PAD]": 36,
+    "[UNK]": 35,
     "a": 1,
     "b": 2,
     "c": 3,
     "d": 4,
     "e": 5,
-    "g": 6,
-    "h": 7,
-    "i": 8,
-    "k": 9,
-    "l": 10,
-    "m": 11,
-    "n": 12,
-    "o": 13,
-    "p": 14,
-    "q": 15,
-    "r": 16,
-    "s": 17,
-    "t": 18,
-    "u": 19,
-    "v": 20,
-    "x": 21,
-    "y": 22,
+    "f": 6,
+    "g": 7,
+    "h": 8,
+    "i": 9,
+    "j": 10,
+    "k": 11,
+    "l": 12,
+    "m": 13,
+    "n": 14,
+    "o": 15,
+    "p": 16,
+    "q": 17,
+    "r": 18,
+    "s": 19,
+    "t": 20,
+    "u": 21,
+    "v": 22,
+    "w": 23,
+    "x": 24,
+    "y": 25,
+    "z": 26,
     "|": 0,
-    "à": 23,
-    "á": 24,
-    "ã": 25,
-    "è": 26,
-    "é": 27,
-    "ê": 28,
-    "ì": 29,
-    "í": 30,
-    "ò": 31,
-    "ó": 32,
-    "õ": 33,
-    "ù": 34,
-    "ú": 35,
-    "ý": 36,
-    "ă": 37,
-    "đ": 38,
-    "ĩ": 39,
-    "ũ": 40,
-    "ơ": 41,
-    "ư": 42,
-    "ạ": 43,
-    "ả": 44,
-    "ấ": 45,
-    "ầ": 46,
-    "ẩ": 47,
-    "ẫ": 48,
-    "ậ": 49,
-    "ắ": 50,
-    "ằ": 51,
-    "ẳ": 52,
-    "ẵ": 53,
-    "ặ": 54,
-    "ẹ": 55,
-    "ẻ": 56,
-    "ẽ": 57,
-    "ế": 58,
-    "ề": 59,
-    "ể": 60,
-    "ễ": 61,
-    "ệ": 62,
-    "ỉ": 63,
-    "ị": 64,
-    "ọ": 65,
-    "ỏ": 66,
-    "ố": 67,
-    "ồ": 68,
-    "ổ": 69,
-    "ỗ": 70,
-    "ộ": 71,
-    "ớ": 72,
-    "ờ": 73,
-    "ở": 74,
-    "ỡ": 75,
-    "ợ": 76,
-    "ụ": 77,
-    "ủ": 78,
-    "ứ": 79,
-    "ừ": 80,
-    "ử": 81,
-    "ữ": 82,
-    "ự": 83,
-    "ỳ": 84,
-    "ỷ": 85,
-    "ỹ": 86
+    "ç": 27,
+    "ë": 28,
+    "ö": 29,
+    "ü": 30,
+    "ğ": 31,
+    "ı": 32,
+    "ş": 33,
+    "̇": 34
   }
 }