add tokenizer
Browse files- added_tokens.json +1 -1
- vocab.json +1 -1
added_tokens.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"<s>":
|
|
|
1 |
+
{"<s>": 98, "</s>": 99}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"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, "
|
|
|
1 |
+
{"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, "q": 47, "आ": 48, "f": 49, "ख": 50, "ॅ": 51, "छ": 52, "s": 53, "j": 54, "i": 55, "त": 56, "x": 57, "फ़": 58, "ड": 59, "ट": 60, "ह": 61, "प": 62, "ृ": 63, "ष": 64, "फ": 65, "ि": 66, "k": 67, "m": 68, "ढ़": 69, "ो": 70, "झ": 71, "l": 72, "b": 73, "ऑ": 74, "u": 75, "c": 76, "थ": 77, "ख़": 78, "ज़": 79, "न": 80, "स": 81, "द": 82, "्": 83, "ञ": 84, "y": 85, "z": 86, "श": 87, "ए": 88, "ब": 89, "ई": 90, "ु": 91, "a": 92, "ौ": 93, "व": 94, "ं": 95, "|": 19, "[UNK]": 96, "[PAD]": 97}
|