Upload tokenizer

added_tokens.json

@@ -1,4 +1,4 @@
 {
-  "</s>": 76,
-  "<s>": 75
+  "</s>": 59,
+  "<s>": 58
 }

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "73": {
+    "56": {
       "content": "[UNK]",
       "lstrip": true,
       "normalized": false,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": false
     },
-    "74": {
+    "57": {
       "content": "[PAD]",
       "lstrip": true,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": false
     },
-    "75": {
+    "58": {
       "content": "<s>",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "76": {
+    "59": {
       "content": "</s>",
       "lstrip": false,
       "normalized": false,

vocab.json

@@ -1,77 +1,60 @@
 {
-  "C": 1,
-  "G": 2,
-  "H": 3,
-  "N": 4,
-  "S": 5,
-  "T": 6,
-  "W": 7,
-  "[PAD]": 74,
-  "[UNK]": 73,
-  "a": 8,
-  "b": 9,
-  "c": 10,
-  "e": 11,
-  "g": 12,
-  "h": 13,
-  "i": 14,
-  "l": 15,
-  "m": 16,
-  "n": 17,
-  "o": 18,
-  "r": 19,
-  "s": 20,
-  "t": 21,
-  "u": 22,
-  "v": 23,
+  "S": 1,
+  "T": 2,
+  "[PAD]": 57,
+  "[UNK]": 56,
+  "a": 3,
+  "g": 4,
+  "i": 5,
+  "n": 6,
+  "o": 7,
+  "t": 8,
   "|": 0,
-  "ஃ": 24,
-  "அ": 25,
-  "ஆ": 26,
-  "இ": 27,
-  "ஈ": 28,
-  "உ": 29,
-  "ஊ": 30,
-  "எ": 31,
-  "ஏ": 32,
-  "ஐ": 33,
-  "ஒ": 34,
-  "ஓ": 35,
-  "க": 36,
-  "ங": 37,
-  "ச": 38,
-  "ஜ": 39,
-  "ஞ": 40,
-  "ட": 41,
-  "ண": 42,
-  "த": 43,
-  "ந": 44,
-  "ன": 45,
-  "ப": 46,
-  "ம": 47,
-  "ய": 48,
-  "ர": 49,
-  "ற": 50,
-  "ல": 51,
-  "ள": 52,
-  "ழ": 53,
-  "வ": 54,
-  "ஷ": 55,
-  "ஸ": 56,
-  "ஹ": 57,
-  "ா": 58,
-  "ி": 59,
-  "ீ": 60,
-  "ு": 61,
-  "ூ": 62,
-  "ெ": 63,
-  "ே": 64,
-  "ை": 65,
-  "ொ": 66,
-  "ோ": 67,
-  "ௌ": 68,
-  "்": 69,
-  "—": 70,
-  "’": 71,
-  "●": 72
+  "ஃ": 9,
+  "அ": 10,
+  "ஆ": 11,
+  "இ": 12,
+  "ஈ": 13,
+  "உ": 14,
+  "ஊ": 15,
+  "எ": 16,
+  "ஏ": 17,
+  "ஐ": 18,
+  "ஒ": 19,
+  "ஓ": 20,
+  "க": 21,
+  "ங": 22,
+  "ச": 23,
+  "ஜ": 24,
+  "ஞ": 25,
+  "ட": 26,
+  "ண": 27,
+  "த": 28,
+  "ந": 29,
+  "ன": 30,
+  "ப": 31,
+  "ம": 32,
+  "ய": 33,
+  "ர": 34,
+  "ற": 35,
+  "ல": 36,
+  "ள": 37,
+  "ழ": 38,
+  "வ": 39,
+  "ஷ": 40,
+  "ஸ": 41,
+  "ஹ": 42,
+  "ா": 43,
+  "ி": 44,
+  "ீ": 45,
+  "ு": 46,
+  "ூ": 47,
+  "ெ": 48,
+  "ே": 49,
+  "ை": 50,
+  "ொ": 51,
+  "ோ": 52,
+  "ௌ": 53,
+  "்": 54,
+  "’": 55
 }