Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 111,
-  "<s>": 110
+  "</s>": 118,
+  "<s>": 117
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "107": {
+    "114": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "108": {
+    "115": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "110": {
+    "117": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "111": {
+    "118": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,7 +1,7 @@
 {
   " ": 0,
-  "[PAD]": 108,
-  "[UNK]": 107,
+  "[PAD]": 115,
+  "[UNK]": 114,
   "a": 1,
   "b": 2,
   "d": 3,
@@ -11,102 +11,109 @@
   "r": 7,
   "t": 8,
   "y": 9,
-  "|": 109,
-  "ं": 10,
-  "अ": 11,
-  "आ": 12,
-  "इ": 13,
-  "ई": 14,
-  "उ": 15,
-  "ऊ": 16,
-  "ए": 17,
-  "ऐ": 18,
-  "ओ": 19,
-  "क": 20,
-  "ख": 21,
-  "ग": 22,
-  "च": 23,
-  "छ": 24,
-  "ज": 25,
-  "ट": 26,
-  "ड": 27,
-  "ण": 28,
-  "त": 29,
-  "थ": 30,
-  "द": 31,
-  "ध": 32,
-  "न": 33,
-  "प": 34,
-  "फ": 35,
-  "ब": 36,
-  "भ": 37,
-  "म": 38,
-  "य": 39,
-  "र": 40,
-  "ल": 41,
-  "व": 42,
-  "श": 43,
-  "ष": 44,
-  "स": 45,
-  "ह": 46,
-  "़": 47,
-  "ा": 48,
-  "ि": 49,
-  "ी": 50,
-  "ु": 51,
-  "ू": 52,
-  "े": 53,
-  "ै": 54,
-  "ॉ": 55,
-  "ो": 56,
-  "ौ": 57,
-  "्": 58,
-  "ం": 59,
-  "అ": 60,
-  "ఆ": 61,
-  "ఇ": 62,
-  "ఈ": 63,
-  "ఉ": 64,
-  "ఎ": 65,
-  "ఏ": 66,
-  "ఒ": 67,
-  "క": 68,
-  "ఖ": 69,
-  "గ": 70,
-  "ఘ": 71,
-  "చ": 72,
-  "జ": 73,
-  "ట": 74,
-  "డ": 75,
-  "ణ": 76,
-  "త": 77,
-  "థ": 78,
-  "ద": 79,
-  "ధ": 80,
-  "న": 81,
-  "ప": 82,
-  "బ": 83,
-  "భ": 84,
-  "మ": 85,
-  "య": 86,
-  "ర": 87,
-  "ల": 88,
-  "ళ": 89,
-  "వ": 90,
-  "శ": 91,
-  "ష": 92,
-  "స": 93,
-  "హ": 94,
-  "ా": 95,
-  "ి": 96,
-  "ీ": 97,
-  "ు": 98,
-  "ృ": 99,
-  "ె": 100,
-  "ే": 101,
-  "ై": 102,
-  "ొ": 103,
-  "ో": 104,
-  "్": 105,
-  "’": 106
+  "|": 116,
+  "ँ": 10,
+  "ं": 11,
+  "अ": 12,
+  "आ": 13,
+  "इ": 14,
+  "ई": 15,
+  "उ": 16,
+  "ऊ": 17,
+  "ए": 18,
+  "ऐ": 19,
+  "ओ": 20,
+  "औ": 21,
+  "क": 22,
+  "ख": 23,
+  "ग": 24,
+  "च": 25,
+  "छ": 26,
+  "ज": 27,
+  "झ": 28,
+  "ट": 29,
+  "ठ": 30,
+  "ड": 31,
+  "ढ": 32,
+  "ण": 33,
+  "त": 34,
+  "थ": 35,
+  "द": 36,
+  "ध": 37,
+  "न": 38,
+  "प": 39,
+  "फ": 40,
+  "ब": 41,
+  "भ": 42,
+  "म": 43,
+  "य": 44,
+  "र": 45,
+  "ल": 46,
+  "व": 47,
+  "श": 48,
+  "ष": 49,
+  "स": 50,
+  "ह": 51,
+  "़": 52,
+  "ा": 53,
+  "ि": 54,
+  "ी": 55,
+  "ु": 56,
+  "ू": 57,
+  "े": 58,
+  "ै": 59,
+  "ॉ": 60,
+  "ो": 61,
+  "ौ": 62,
+  "्": 63,
+  "ड़": 64,
+  "ం": 65,
+  "అ": 66,
+  "ఆ": 67,
+  "ఇ": 68,
+  "ఉ": 69,
+  "ఎ": 70,
+  "ఏ": 71,
+  "ఒ": 72,
+  "క": 73,
+  "ఖ": 74,
+  "గ": 75,
+  "ఘ": 76,
+  "చ": 77,
+  "జ": 78,
+  "ట": 79,
+  "డ": 80,
+  "ణ": 81,
+  "త": 82,
+  "థ": 83,
+  "ద": 84,
+  "ధ": 85,
+  "న": 86,
+  "ప": 87,
+  "ఫ": 88,
+  "బ": 89,
+  "భ": 90,
+  "మ": 91,
+  "య": 92,
+  "ర": 93,
+  "ల": 94,
+  "ళ": 95,
+  "వ": 96,
+  "శ": 97,
+  "ష": 98,
+  "స": 99,
+  "హ": 100,
+  "ా": 101,
+  "ి": 102,
+  "ీ": 103,
+  "ు": 104,
+  "ూ": 105,
+  "ృ": 106,
+  "ె": 107,
+  "ే": 108,
+  "ై": 109,
+  "ొ": 110,
+  "ో": 111,
+  "ౌ": 112,
+  "్": 113
 }