add tokenizer

vocab.json

@@ -1 +1 @@
-{"ூ": 0, "ே": 1, "ு": 2, "ஊ": 3, "ர": 4, "ந": 5, "ஸ": 6, "ஷ": 7, "ப": 8, "ெ": 9, "ஔ": 10, "ஈ": 11, "ஐ": 12, "வ": 14, "’": 15, "ற": 16, "அ": 17, "ை": 18, "க": 19, "ட": 20, "ம": 21, "்": 22, "ய": 23, "ோ": 24, "ஒ": 25, "எ": 26, "ள": 27, "த": 28, "உ": 29, "ல": 30, "ி": 31, "ஜ": 32, "ஞ": 33, "ா": 34, "ச": 35, "ஓ": 36, "ங": 37, "ீ": 38, "ஹ": 39, "ழ": 40, "இ": 41, "ஏ": 42, "ௌ": 43, "ொ": 44, "'": 45, "ஆ": 46, "ண": 47, "ன": 48, "ஃ": 49, "|": 13, "[UNK]": 50, "[PAD]": 51}
+{"ீ": 0, "'": 1, "ு": 2, "த": 3, "ஞ": 4, "ி": 5, "ய": 6, "உ": 7, "ஒ": 8, "ை": 9, "ோ": 10, "ா": 11, "ஜ": 12, "ம": 13, "ஈ": 14, "ழ": 15, "ஏ": 16, "ல": 17, "ங": 18, "ள": 19, "ொ": 20, "ப": 21, "ஃ": 22, "ஆ": 23, "ூ": 24, "்": 25, "ௌ": 26, "ட": 27, "ஐ": 28, "அ": 29, "’": 30, "ெ": 31, "ற": 32, "ண": 33, "ச": 34, "வ": 35, "ஸ": 36, "ஔ": 37, "ன": 38, "ஷ": 39, "ஓ": 40, "ர": 41, "எ": 42, "ே": 44, "ஊ": 45, "ஹ": 46, "ந": 47, "இ": 48, "க": 49, "|": 43, "[UNK]": 50, "[PAD]": 51}