Upload tokenizer
59412c7
verified
|
{ |
|
"$": 98, |
|
"&": 51, |
|
"'": 31, |
|
"(": 3, |
|
"-": 82, |
|
"F": 45, |
|
"L": 11, |
|
"N": 20, |
|
"R": 22, |
|
"Y": 83, |
|
"[": 72, |
|
"[FR]": 102, |
|
"[FY-NL]": 101, |
|
"[PAD]": 100, |
|
"[UNK]": 99, |
|
"]": 21, |
|
"a": 76, |
|
"b": 88, |
|
"c": 12, |
|
"d": 70, |
|
"e": 35, |
|
"f": 80, |
|
"g": 64, |
|
"h": 74, |
|
"i": 47, |
|
"j": 13, |
|
"k": 55, |
|
"l": 91, |
|
"m": 66, |
|
"n": 30, |
|
"o": 8, |
|
"p": 59, |
|
"q": 90, |
|
"r": 37, |
|
"s": 44, |
|
"t": 77, |
|
"u": 68, |
|
"v": 26, |
|
"w": 69, |
|
"x": 5, |
|
"y": 25, |
|
"z": 6, |
|
"|": 95, |
|
"~": 52, |
|
"«": 42, |
|
"´": 10, |
|
"»": 32, |
|
"à": 33, |
|
"á": 46, |
|
"â": 86, |
|
"ã": 84, |
|
"ä": 9, |
|
"å": 39, |
|
"æ": 57, |
|
"ç": 23, |
|
"è": 7, |
|
"é": 18, |
|
"ê": 15, |
|
"ë": 14, |
|
"í": 0, |
|
"î": 60, |
|
"ï": 62, |
|
"ñ": 4, |
|
"ó": 40, |
|
"ô": 65, |
|
"ö": 63, |
|
"ø": 24, |
|
"ù": 71, |
|
"ú": 93, |
|
"û": 79, |
|
"ü": 43, |
|
"ā": 94, |
|
"ă": 1, |
|
"ć": 34, |
|
"č": 27, |
|
"ę": 92, |
|
"ĝ": 48, |
|
"ł": 56, |
|
"ō": 81, |
|
"ő": 85, |
|
"œ": 16, |
|
"ś": 49, |
|
"ş": 73, |
|
"š": 58, |
|
"ū": 41, |
|
"ż": 50, |
|
"ž": 67, |
|
"ș": 29, |
|
"ʿ": 89, |
|
"ː": 36, |
|
"̀": 61, |
|
"́": 96, |
|
"̂": 87, |
|
"̧": 28, |
|
"–": 19, |
|
"—": 17, |
|
"‘": 78, |
|
"’": 97, |
|
"…": 38, |
|
"ℤ": 53, |
|
"保": 75, |
|
"宇": 54, |
|
"津": 2 |
|
} |
|
|