Add Tamil character support to tokenizer - 62 Tamil characters including vowels, consonants, Grantha characters, vowel markers, and digits
19d5c9a verified | { | |
| "version": "1.0", | |
| "model": { | |
| "type": "WordLevel", | |
| "vocab": { | |
| "[UNK]": 0, | |
| "[START]": 1, | |
| "[STOP]": 2, | |
| "[SPACE]": 3, | |
| "[PAD]": 4, | |
| "[CLS]": 5, | |
| "[SEP]": 6, | |
| "a": 7, | |
| "b": 8, | |
| "c": 9, | |
| "d": 10, | |
| "e": 11, | |
| "f": 12, | |
| "g": 13, | |
| "h": 14, | |
| "i": 15, | |
| "j": 16, | |
| "k": 17, | |
| "l": 18, | |
| "m": 19, | |
| "n": 20, | |
| "o": 21, | |
| "p": 22, | |
| "q": 23, | |
| "r": 24, | |
| "s": 25, | |
| "t": 26, | |
| "u": 27, | |
| "v": 28, | |
| "w": 29, | |
| "x": 30, | |
| "y": 31, | |
| "z": 32, | |
| "A": 33, | |
| "B": 34, | |
| "C": 35, | |
| "D": 36, | |
| "E": 37, | |
| "F": 38, | |
| "G": 39, | |
| "H": 40, | |
| "I": 41, | |
| "J": 42, | |
| "K": 43, | |
| "L": 44, | |
| "M": 45, | |
| "N": 46, | |
| "O": 47, | |
| "P": 48, | |
| "Q": 49, | |
| "R": 50, | |
| "S": 51, | |
| "T": 52, | |
| "U": 53, | |
| "V": 54, | |
| "W": 55, | |
| "X": 56, | |
| "Y": 57, | |
| "Z": 58, | |
| "0": 59, | |
| "1": 60, | |
| "2": 61, | |
| "3": 62, | |
| "4": 63, | |
| "5": 64, | |
| "6": 65, | |
| "7": 66, | |
| "8": 67, | |
| "9": 68, | |
| ".": 69, | |
| ",": 70, | |
| "!": 71, | |
| "?": 72, | |
| ";": 73, | |
| ":": 74, | |
| "'": 75, | |
| "\"": 76, | |
| "(": 77, | |
| ")": 78, | |
| "-": 79, | |
| " ": 80, | |
| "அ": 81, | |
| "ஆ": 82, | |
| "இ": 83, | |
| "ஈ": 84, | |
| "உ": 85, | |
| "ஊ": 86, | |
| "எ": 87, | |
| "ஏ": 88, | |
| "ஐ": 89, | |
| "ஒ": 90, | |
| "ஓ": 91, | |
| "ஔ": 92, | |
| "க": 93, | |
| "ங": 94, | |
| "ச": 95, | |
| "ஞ": 96, | |
| "ட": 97, | |
| "ண": 98, | |
| "த": 99, | |
| "ந": 100, | |
| "ப": 101, | |
| "ம": 102, | |
| "ய": 103, | |
| "ர": 104, | |
| "ல": 105, | |
| "வ": 106, | |
| "ழ": 107, | |
| "ள": 108, | |
| "ற": 109, | |
| "ன": 110, | |
| "ஜ": 111, | |
| "ஷ": 112, | |
| "ஸ": 113, | |
| "ஹ": 114, | |
| "க்ஷ": 115, | |
| "ஸ்ரீ": 116, | |
| "ா": 117, | |
| "ி": 118, | |
| "ீ": 119, | |
| "ு": 120, | |
| "ூ": 121, | |
| "ெ": 122, | |
| "ே": 123, | |
| "ை": 124, | |
| "ொ": 125, | |
| "ோ": 126, | |
| "ௌ": 127, | |
| "்": 128, | |
| "௦": 129, | |
| "௧": 130, | |
| "௨": 131, | |
| "௩": 132, | |
| "௪": 133, | |
| "௫": 134, | |
| "௬": 135, | |
| "௭": 136, | |
| "௮": 137, | |
| "௯": 138, | |
| "ௗ": 139, | |
| "௰": 140, | |
| "௱": 141, | |
| "௲": 142 | |
| }, | |
| "unk_token": "[UNK]" | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Whitespace" | |
| }, | |
| "normalizer": { | |
| "type": "NFKC" | |
| } | |
| } |