{ | |
"version": "1.0", | |
"truncation": null, | |
"padding": null, | |
"added_tokens": [ | |
{ | |
"id": 34, | |
"content": "<unk>", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
} | |
], | |
"normalizer": { | |
"type": "Sequence", | |
"normalizers": [ | |
{ | |
"type": "Lowercase" | |
}, | |
{ | |
"type": "Replace", | |
"pattern": { | |
"String": "\u021b" | |
}, | |
"content": "\u0163" | |
}, | |
{ | |
"type": "Replace", | |
"pattern": { | |
"Regex": "[^cqubg_n\u2013mzitl\u0103f\u0219a1\u00eep\\-hs'xej\u00e2 rvo\u0163d]" | |
}, | |
"content": "" | |
}, | |
{ | |
"type": "Strip", | |
"strip_left": true, | |
"strip_right": true | |
}, | |
{ | |
"type": "Replace", | |
"pattern": { | |
"Regex": "(?=.)|(?<!^)$" | |
}, | |
"content": "c" | |
} | |
] | |
}, | |
"pre_tokenizer": { | |
"type": "Split", | |
"pattern": { | |
"Regex": "" | |
}, | |
"behavior": "Isolated", | |
"invert": false | |
}, | |
"post_processor": null, | |
"decoder": null, | |
"model": { | |
"vocab": { | |
"c": 0, | |
"q": 1, | |
"u": 2, | |
"b": 3, | |
"g": 4, | |
"_": 5, | |
"n": 6, | |
"\u2013": 7, | |
"m": 8, | |
"z": 9, | |
"i": 10, | |
"t": 11, | |
"l": 12, | |
"\u0103": 13, | |
"f": 14, | |
"\u0219": 15, | |
"a": 16, | |
"1": 17, | |
"\u00ee": 18, | |
"p": 19, | |
"-": 20, | |
"h": 21, | |
"s": 22, | |
"'": 23, | |
"x": 24, | |
"e": 25, | |
"j": 26, | |
"\u00e2": 27, | |
" ": 28, | |
"r": 29, | |
"v": 30, | |
"o": 31, | |
"\u0163": 32, | |
"d": 33, | |
"<unk>": 34 | |
} | |
} | |
} |