Upload tokenizer
17c6f1a
verified
|
{ |
|
"tur": { |
|
"&": 1, |
|
"(": 2, |
|
")": 3, |
|
"[PAD]": 99, |
|
"[UNK]": 98, |
|
"\\": 4, |
|
"_": 5, |
|
"`": 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, |
|
"|": 0, |
|
"·": 33, |
|
"½": 34, |
|
"¾": 35, |
|
"á": 36, |
|
"é": 37, |
|
"š": 38, |
|
"ஃ": 39, |
|
"அ": 40, |
|
"ஆ": 41, |
|
"இ": 42, |
|
"ஈ": 43, |
|
"உ": 44, |
|
"ஊ": 45, |
|
"எ": 46, |
|
"ஏ": 47, |
|
"ஐ": 48, |
|
"ஒ": 49, |
|
"ஓ": 50, |
|
"ஔ": 51, |
|
"க": 52, |
|
"ங": 53, |
|
"ச": 54, |
|
"ஜ": 55, |
|
"ஞ": 56, |
|
"ட": 57, |
|
"ண": 58, |
|
"த": 59, |
|
"ந": 60, |
|
"ன": 61, |
|
"ப": 62, |
|
"ம": 63, |
|
"ய": 64, |
|
"ர": 65, |
|
"ற": 66, |
|
"ல": 67, |
|
"ள": 68, |
|
"ழ": 69, |
|
"வ": 70, |
|
"ஷ": 71, |
|
"ஸ": 72, |
|
"ஹ": 73, |
|
"ா": 74, |
|
"ி": 75, |
|
"ீ": 76, |
|
"ு": 77, |
|
"ூ": 78, |
|
"ெ": 79, |
|
"ே": 80, |
|
"ை": 81, |
|
"ொ": 82, |
|
"ோ": 83, |
|
"ௌ": 84, |
|
"்": 85, |
|
"ௗ": 86, |
|
"ഥ": 87, |
|
"–": 88, |
|
"—": 89, |
|
"’": 90, |
|
"‚": 91, |
|
"•": 92, |
|
"…": 93, |
|
"′": 94, |
|
"″": 95, |
|
"●": 96, |
|
"◯": 97 |
|
} |
|
} |
|
|