bert-base-cantonese / added_tokens.json
indiejoseph's picture
Training in progress, step 500
2faa264
raw
history blame
No virus
8 kB
{
"㕔": 21619,
"㚻": 21188,
"㞗": 21218,
"㞘": 21469,
"㩒": 21294,
"㴓": 21464,
"㶲": 21567,
"㷫": 21317,
"䊦": 21490,
"䘆": 21524,
"乸": 21138,
"亶": 21536,
"仫": 21529,
"佮": 21215,
"偲": 21192,
"傕": 21558,
"僆": 21393,
"僞": 21568,
"儁": 21423,
"儇": 21566,
"兗": 21314,
"冚": 21137,
"冧": 21135,
"勗": 21501,
"勲": 21461,
"勷": 21507,
"卌": 21220,
"卽": 21156,
"叄": 21595,
"吔": 21470,
"吲": 21400,
"呔": 21195,
"咇": 21398,
"哚": 21362,
"唂": 21261,
"唞": 21212,
"唥": 21142,
"唨": 21182,
"唪": 21145,
"唻": 21231,
"啹": 21586,
"喐": 21150,
"喥": 21428,
"喦": 21562,
"喼": 21376,
"嗌": 21130,
"嗮": 21131,
"嗱": 21282,
"嘥": 21166,
"噉": 21129,
"噏": 21234,
"噯": 21599,
"嚙": 21266,
"嚜": 21512,
"嚡": 21397,
"嚦": 21474,
"嚫": 21326,
"嚿": 21132,
"囘": 21419,
"坭": 21223,
"垓": 21585,
"埐": 21224,
"埞": 21181,
"埲": 21267,
"堊": 21244,
"塱": 21171,
"塹": 21430,
"塽": 21623,
"墪": 21555,
"墬": 21576,
"奀": 21614,
"奭": 21306,
"姵": 21508,
"娸": 21297,
"媺": 21374,
"嫗": 21336,
"嬋": 21413,
"嬲": 21159,
"孭": 21194,
"孲": 21179,
"孻": 21225,
"尐": 21148,
"尙": 21525,
"屘": 21564,
"屙": 21184,
"屻": 21590,
"岃": 21274,
"崢": 21457,
"嶠": 21447,
"幗": 21205,
"幪": 21260,
"廄": 21615,
"廸": 21255,
"廻": 21344,
"彊": 21612,
"彔": 21548,
"彖": 21219,
"徂": 21146,
"恂": 21575,
"惗": 21569,
"愃": 21409,
"愨": 21516,
"慤": 21299,
"懽": 21546,
"戇": 21226,
"戙": 21408,
"戥": 21169,
"抌": 21381,
"拃": 21165,
"拏": 21268,
"挐": 21589,
"捹": 21528,
"捽": 21369,
"掕": 21162,
"掟": 21160,
"掹": 21291,
"掾": 21559,
"揈": 21407,
"揞": 21513,
"揼": 21180,
"揾": 21151,
"搣": 21333,
"搲": 21418,
"摱": 21600,
"摷": 21305,
"撘": 21487,
"撳": 21155,
"撾": 21149,
"擸": 21456,
"攋": 21410,
"攰": 21240,
"攴": 21504,
"攷": 21128,
"旚": 21367,
"旯": 21237,
"旼": 21571,
"昃": 21416,
"昑": 21479,
"昪": 21436,
"昰": 21366,
"昺": 21290,
"暎": 21477,
"暦": 21626,
"曚": 21607,
"曱": 21246,
"曺": 21492,
"朊": 21579,
"朏": 21424,
"柊": 21582,
"栢": 21170,
"栱": 21427,
"桕": 21535,
"桫": 21510,
"梘": 21228,
"椏": 21270,
"椗": 21594,
"樅": 21429,
"樋": 21361,
"樖": 21136,
"樘": 21578,
"樨": 21301,
"橈": 21597,
"橛": 21147,
"檠": 21230,
"櫈": 21211,
"櫟": 21368,
"櫳": 21236,
"欏": 21476,
"殮": 21202,
"殻": 21404,
"毬": 21624,
"氘": 21451,
"氚": 21460,
"氬": 21328,
"氼": 21238,
"沊": 21495,
"沔": 21609,
"沚": 21293,
"泂": 21324,
"淥": 21502,
"淯": 21591,
"淸": 21300,
"湉": 21327,
"湞": 21356,
"湴": 21391,
"湼": 21471,
"滘": 21143,
"漖": 21354,
"潁": 21307,
"潯": 21206,
"潽": 21458,
"澌": 21318,
"濊": 21606,
"濰": 21198,
"濶": 21604,
"灃": 21539,
"灕": 21275,
"炆": 21222,
"炘": 21385,
"烚": 21440,
"烴": 21164,
"焓": 21455,
"焫": 21540,
"煇": 21189,
"煠": 21493,
"煬": 21308,
"燶": 21514,
"燾": 21570,
"牀": 21199,
"牘": 21549,
"犂": 21473,
"猢": 21421,
"猻": 21331,
"獴": 21197,
"珓": 21258,
"琚": 21422,
"琤": 21389,
"琿": 21377,
"瑂": 21444,
"瑭": 21352,
"璘": 21347,
"璠": 21251,
"璣": 21233,
"璦": 21437,
"璩": 21383,
"瓘": 21511,
"瓚": 21312,
"甂": 21350,
"甑": 21335,
"甴": 21259,
"畧": 21253,
"畵": 21303,
"疎": 21401,
"疴": 21338,
"痲": 21587,
"痾": 21214,
"癆": 21396,
"癩": 21459,
"睺": 21243,
"睼": 21452,
"瞽": 21560,
"砵": 21176,
"硃": 21485,
"硏": 21403,
"硤": 21163,
"碲": 21583,
"礬": 21466,
"礮": 21276,
"祆": 21494,
"祘": 21545,
"禕": 21499,
"禤": 21467,
"禰": 21552,
"稈": 21252,
"穏": 21316,
"窰": 21178,
"竈": 21379,
"竉": 21210,
"笪": 21134,
"篋": 21613,
"篾": 21496,
"簋": 21621,
"簒": 21287,
"簕": 21351,
"糭": 21232,
"糴": 21554,
"糶": 21532,
"紇": 21380,
"紥": 21348,
"綉": 21503,
"綝": 21592,
"綟": 21273,
"綷": 21488,
"緡": 21193,
"縉": 21295,
"縞": 21434,
"繙": 21183,
"缶": 21563,
"罅": 21177,
"罉": 21340,
"罘": 21544,
"罟": 21248,
"羋": 21521,
"羕": 21482,
"翕": 21360,
"耖": 21574,
"胐": 21249,
"脧": 21221,
"脷": 21139,
"腍": 21537,
"膥": 21191,
"膶": 21304,
"臏": 21445,
"舘": 21269,
"茛": 21375,
"莨": 21515,
"菫": 21505,
"菴": 21216,
"葰": 21526,
"葶": 21185,
"蒯": 21601,
"蒴": 21239,
"蓀": 21448,
"蔴": 21154,
"蕓": 21322,
"藪": 21245,
"藶": 21190,
"藺": 21509,
"蘅": 21392,
"蚺": 21520,
"蛺": 21313,
"蜑": 21256,
"蜞": 21417,
"螈": 21390,
"蟌": 21263,
"蟝": 21605,
"蟧": 21395,
"蠄": 21302,
"蠏": 21311,
"蠑": 21538,
"裀": 21618,
"裇": 21288,
"褦": 21200,
"褸": 21172,
"覲": 21319,
"觜": 21358,
"訃": 21420,
"訌": 21518,
"訢": 21465,
"詏": 21284,
"詒": 21489,
"諤": 21449,
"謖": 21411,
"謚": 21186,
"謦": 21617,
"謳": 21286,
"譒": 21565,
"谿": 21431,
"豕": 21450,
"豸": 21584,
"貍": 21472,
"贇": 21602,
"跣": 21345,
"踎": 21196,
"踭": 21203,
"躄": 21144,
"軚": 21241,
"軛": 21321,
"軫": 21242,
"軻": 21577,
"輋": 21187,
"迾": 21441,
"逑": 21355,
"逳": 21174,
"遯": 21550,
"郃": 21517,
"郾": 21439,
"鄕": 21364,
"鄴": 21281,
"酆": 21622,
"酎": 21556,
"釔": 21588,
"釙": 21443,
"釩": 21625,
"釷": 21527,
"釹": 21533,
"鈁": 21593,
"鈧": 21610,
"鈷": 21432,
"鈸": 21561,
"鈹": 21386,
"鉍": 21480,
"鉞": 21372,
"鉬": 21442,
"鉸": 21271,
"鉼": 21296,
"銚": 21553,
"銣": 21478,
"銥": 21446,
"銦": 21453,
"銨": 21339,
"銫": 21298,
"銲": 21608,
"銶": 21486,
"銻": 21388,
"銼": 21292,
"鋇": 21373,
"鋯": 21596,
"鋹": 21581,
"錒": 21262,
"錕": 21433,
"錡": 21227,
"鍔": 21359,
"鍬": 21384,
"鍶": 21278,
"鎅": 21365,
"鎘": 21481,
"鎢": 21310,
"鎭": 21627,
"鎵": 21435,
"鏇": 21415,
"鏐": 21483,
"鏵": 21406,
"鏸": 21620,
"鏹": 21542,
"鐖": 21572,
"鑌": 21438,
"鑭": 21285,
"鑴": 21497,
"閂": 21158,
"閆": 21412,
"閪": 21329,
"閬": 21402,
"閭": 21279,
"闐": 21213,
"闓": 21484,
"阬": 21551,
"阯": 21541,
"陜": 21468,
"靑": 21342,
"靺": 21580,
"鞨": 21611,
"韃": 21209,
"韞": 21353,
"頊": 21330,
"頴": 21229,
"顓": 21454,
"顥": 21309,
"顳": 21289,
"餬": 21207,
"餸": 21152,
"饉": 21519,
"馱": 21387,
"駟": 21414,
"騫": 21173,
"騭": 21349,
"騮": 21157,
"騾": 21506,
"驃": 21250,
"驄": 21277,
"驤": 21543,
"骹": 21378,
"髀": 21168,
"髙": 21547,
"髹": 21332,
"鬅": 21235,
"鬩": 21500,
"鬭": 21394,
"鬯": 21598,
"鬲": 21343,
"魨": 21346,
"鮎": 21603,
"鮟": 21141,
"鮫": 21531,
"鯇": 21523,
"鯡": 21573,
"鯥": 21475,
"鯪": 21257,
"鯭": 21371,
"鰂": 21167,
"鰕": 21201,
"鰹": 21323,
"鱇": 21140,
"鱒": 21498,
"鱘": 21382,
"鱟": 21491,
"鱲": 21175,
"鳽": 21557,
"鴇": 21265,
"鴞": 21254,
"鴣": 21426,
"鴴": 21283,
"鴷": 21337,
"鵐": 21208,
"鵞": 21399,
"鵪": 21530,
"鶇": 21204,
"鶉": 21334,
"鶚": 21534,
"鶿": 21341,
"鷂": 21280,
"鷄": 21161,
"鷈": 21463,
"鷓": 21425,
"鷸": 21363,
"鷿": 21462,
"鸕": 21320,
"鸛": 21272,
"麪": 21133,
"麿": 21217,
"黐": 21153,
"鼆": 21264,
"鼇": 21522,
"鼩": 21325,
"鼴": 21247,
"鼷": 21315,
"齶": 21616,
"龑": 21405,
"龠": 21370,
"龢": 21357
}