add tokenizer

added_tokens.json

@@ -1 +1 @@
-{"<s>": 94, "</s>": 95}
+{"<s>": 95, "</s>": 96}

vocab.json

@@ -1 +1 @@
-{"ऑ": 0, "ग": 1, "ल": 2, "n": 3, "म": 4, "b": 5, "ढ़": 6, "ॉ": 7, "i": 8, "ऋ": 9, "भ": 10, "े": 11, "ई": 12, "फ": 13, "z": 14, "य": 15, "ं": 16, "ः": 17, "ड": 18, "द": 19, "ा": 20, "थ": 21, "ृ": 22, "व": 23, "v": 24, "्": 25, "ॅ": 26, "ऐ": 27, "ष": 28, "ब": 29, "r": 30, "d": 31, "अ": 32, "आ": 33, "ज़": 34, "ञ": 35, "m": 36, "t": 37, "श": 38, "g": 39, "k": 40, "ठ": 41, "y": 42, "|": 57, "ण": 44, "ध": 45, "।": 46, "ि": 47, "ी": 48, "ढ": 49, "ू": 50, "a": 51, "h": 52, "ँ": 53, "j": 54, "f": 55, "झ": 56, "l": 58, "ह": 59, "e": 60, "s": 61, "घ": 62, "ु": 63, "ज": 64, "w": 65, "ट": 66, "ो": 67, "स": 68, "छ": 69, "ऊ": 70, "न": 71, "प": 72, "ौ": 73, "ओ": 74, "u": 75, "इ": 76, "उ": 77, "o": 78, "ए": 79, "p": 80, "ड़": 81, "औ": 82, "ै": 83, "क़": 84, "x": 85, "ग़": 86, "र": 87, "ख": 88, "c": 89, "क": 90, "त": 91, "़": 92, "च": 93, "[UNK]": 93, "[PAD]": 94}
+{"ऐ": 0, "e": 1, "ऊ": 2, "इ": 3, "ल": 4, "उ": 5, "ॉ": 6, "य": 7, "ः": 8, "ू": 9, "v": 10, "'": 11, "म": 12, "ऋ": 13, "ा": 14, "o": 15, "ँ": 16, "ज": 17, "औ": 18, "़": 20, "क़": 21, "ग": 22, "h": 23, "t": 24, "भ": 25, "ग़": 26, "घ": 27, "p": 28, "ध": 29, "र": 30, "w": 31, "ै": 32, "च": 33, "r": 34, "n": 35, "े": 36, "ठ": 37, "ढ": 38, "g": 39, "अ": 40, "ी": 41, "ड़": 42, "ओ": 43, "d": 44, "ण": 45, "क": 46, "आ": 47, "f": 48, "ख": 49, "ॅ": 50, "छ": 51, "s": 52, "j": 53, "i": 54, "त": 55, "x": 56, "ड": 57, "ट": 58, "ह": 59, "प": 60, "ृ": 61, "ष": 62, "फ": 63, "ि": 64, "k": 65, "m": 66, "ढ़": 67, "ो": 68, "झ": 69, "l": 70, "b": 71, "ऑ": 72, "u": 73, "c": 74, "थ": 75, "ज़": 76, "न": 77, "स": 78, "द": 79, "्": 80, "ञ": 81, "y": 82, "z": 83, "श": 84, "ए": 85, "ब": 86, "ई": 87, "ु": 88, "a": 89, "ौ": 90, "व": 91, "ं": 92, "|": 19, "[UNK]": 93, "[PAD]": 94}