Commit
•
9fc91ab
1
Parent(s):
3db724d
Upload 5 files (#3)
Browse files- Upload 5 files (21037892290ef16c31651824c579fa1cf6ce6c0d)
Co-authored-by: fangjun <csukuangfj@users.noreply.huggingface.co>
data/lang_bpe_500/bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c53433de083c4a6ad12d034550ef22de68cec62c4f58932a7b6b8b2f1e743fa5
|
3 |
+
size 244865
|
data/lang_bpe_500/lexicon.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
data/lang_bpe_500/unigram_500.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c53433de083c4a6ad12d034550ef22de68cec62c4f58932a7b6b8b2f1e743fa5
|
3 |
+
size 244865
|
data/lang_bpe_500/unigram_500.vocab
ADDED
@@ -0,0 +1,500 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<blk> 0
|
2 |
+
<sos/eos> 0
|
3 |
+
<unk> 0
|
4 |
+
S -3.23764
|
5 |
+
▁THE -3.39114
|
6 |
+
▁A -3.91235
|
7 |
+
T -3.9788
|
8 |
+
▁AND -4.04148
|
9 |
+
ED -4.06805
|
10 |
+
▁OF -4.11122
|
11 |
+
▁TO -4.14819
|
12 |
+
E -4.15925
|
13 |
+
D -4.19884
|
14 |
+
N -4.28917
|
15 |
+
ING -4.40123
|
16 |
+
▁IN -4.45251
|
17 |
+
Y -4.52708
|
18 |
+
M -4.57919
|
19 |
+
C -4.62646
|
20 |
+
▁I -4.68235
|
21 |
+
A -4.68468
|
22 |
+
P -4.69613
|
23 |
+
▁HE -4.71198
|
24 |
+
R -4.82144
|
25 |
+
O -4.83893
|
26 |
+
L -4.88007
|
27 |
+
RE -4.88603
|
28 |
+
I -4.90352
|
29 |
+
U -4.91157
|
30 |
+
ER -4.95434
|
31 |
+
▁IT -4.99701
|
32 |
+
LY -5.00155
|
33 |
+
▁THAT -5.00795
|
34 |
+
▁WAS -5.04607
|
35 |
+
▁ -5.05486
|
36 |
+
▁S -5.05888
|
37 |
+
AR -5.10129
|
38 |
+
▁BE -5.14569
|
39 |
+
F -5.18181
|
40 |
+
▁C -5.18836
|
41 |
+
IN -5.20029
|
42 |
+
B -5.20859
|
43 |
+
▁FOR -5.23485
|
44 |
+
OR -5.26974
|
45 |
+
LE -5.2702
|
46 |
+
' -5.27032
|
47 |
+
▁HIS -5.28672
|
48 |
+
▁YOU -5.34529
|
49 |
+
AL -5.35383
|
50 |
+
▁RE -5.35863
|
51 |
+
V -5.36811
|
52 |
+
▁B -5.36912
|
53 |
+
G -5.39337
|
54 |
+
RI -5.41681
|
55 |
+
▁E -5.41899
|
56 |
+
▁WITH -5.4268
|
57 |
+
▁T -5.49151
|
58 |
+
▁AS -5.50186
|
59 |
+
LL -5.50605
|
60 |
+
▁P -5.51409
|
61 |
+
▁HER -5.52391
|
62 |
+
ST -5.52898
|
63 |
+
▁HAD -5.53885
|
64 |
+
▁SO -5.56342
|
65 |
+
▁F -5.56472
|
66 |
+
W -5.57126
|
67 |
+
CE -5.61235
|
68 |
+
▁IS -5.63341
|
69 |
+
ND -5.63677
|
70 |
+
▁NOT -5.64685
|
71 |
+
TH -5.65822
|
72 |
+
▁BUT -5.65885
|
73 |
+
EN -5.67118
|
74 |
+
▁SHE -5.67453
|
75 |
+
▁ON -5.67506
|
76 |
+
VE -5.6788
|
77 |
+
ON -5.68108
|
78 |
+
SE -5.68128
|
79 |
+
▁DE -5.68499
|
80 |
+
UR -5.70257
|
81 |
+
▁G -5.70716
|
82 |
+
CH -5.71597
|
83 |
+
K -5.73117
|
84 |
+
TER -5.73588
|
85 |
+
▁AT -5.74333
|
86 |
+
IT -5.75281
|
87 |
+
▁ME -5.75999
|
88 |
+
RO -5.78792
|
89 |
+
NE -5.81237
|
90 |
+
RA -5.84735
|
91 |
+
ES -5.86915
|
92 |
+
IL -5.9164
|
93 |
+
NG -5.95522
|
94 |
+
IC -5.95622
|
95 |
+
▁NO -5.95875
|
96 |
+
▁HIM -5.9632
|
97 |
+
ENT -5.96542
|
98 |
+
IR -5.98727
|
99 |
+
▁WE -6.00283
|
100 |
+
H -6.00505
|
101 |
+
▁DO -6.01678
|
102 |
+
▁ALL -6.0215
|
103 |
+
▁HAVE -6.04155
|
104 |
+
LO -6.04175
|
105 |
+
▁BY -6.0754
|
106 |
+
▁MY -6.07629
|
107 |
+
▁MO -6.07686
|
108 |
+
▁THIS -6.07749
|
109 |
+
LA -6.07936
|
110 |
+
▁ST -6.10084
|
111 |
+
▁WHICH -6.10116
|
112 |
+
▁CON -6.11572
|
113 |
+
▁THEY -6.13378
|
114 |
+
CK -6.13419
|
115 |
+
TE -6.14807
|
116 |
+
▁SAID -6.15974
|
117 |
+
▁FROM -6.16115
|
118 |
+
▁GO -6.16495
|
119 |
+
▁WHO -6.17239
|
120 |
+
▁TH -6.18452
|
121 |
+
▁OR -6.18883
|
122 |
+
▁D -6.18975
|
123 |
+
▁W -6.19439
|
124 |
+
VER -6.20494
|
125 |
+
LI -6.22095
|
126 |
+
▁SE -6.2297
|
127 |
+
▁ONE -6.23026
|
128 |
+
▁CA -6.23397
|
129 |
+
▁AN -6.24262
|
130 |
+
▁LA -6.24786
|
131 |
+
▁WERE -6.24858
|
132 |
+
EL -6.271
|
133 |
+
▁HA -6.28368
|
134 |
+
▁MAN -6.29896
|
135 |
+
▁FA -6.31168
|
136 |
+
▁EX -6.31364
|
137 |
+
AD -6.31526
|
138 |
+
▁SU -6.34091
|
139 |
+
RY -6.35457
|
140 |
+
▁MI -6.37021
|
141 |
+
AT -6.39107
|
142 |
+
▁BO -6.39815
|
143 |
+
▁WHEN -6.40637
|
144 |
+
AN -6.41853
|
145 |
+
THER -6.42115
|
146 |
+
PP -6.43792
|
147 |
+
ATION -6.44105
|
148 |
+
▁FI -6.45761
|
149 |
+
▁WOULD -6.47257
|
150 |
+
▁PRO -6.47274
|
151 |
+
OW -6.48047
|
152 |
+
ET -6.48289
|
153 |
+
▁O -6.48763
|
154 |
+
▁THERE -6.48808
|
155 |
+
▁HO -6.48841
|
156 |
+
ION -6.48846
|
157 |
+
▁WHAT -6.49159
|
158 |
+
▁FE -6.49797
|
159 |
+
▁PA -6.50029
|
160 |
+
US -6.50081
|
161 |
+
MENT -6.50395
|
162 |
+
▁MA -6.50516
|
163 |
+
UT -6.53807
|
164 |
+
▁OUT -6.54596
|
165 |
+
▁THEIR -6.54897
|
166 |
+
▁IF -6.55068
|
167 |
+
▁LI -6.55453
|
168 |
+
▁K -6.56374
|
169 |
+
▁WILL -6.5669
|
170 |
+
▁ARE -6.57477
|
171 |
+
ID -6.57502
|
172 |
+
▁RO -6.57553
|
173 |
+
DE -6.58188
|
174 |
+
TION -6.59518
|
175 |
+
▁WA -6.59566
|
176 |
+
PE -6.60184
|
177 |
+
▁UP -6.60311
|
178 |
+
▁SP -6.61112
|
179 |
+
▁PO -6.61409
|
180 |
+
IGHT -6.63771
|
181 |
+
▁UN -6.64183
|
182 |
+
RU -6.64252
|
183 |
+
▁LO -6.64639
|
184 |
+
AS -6.64889
|
185 |
+
OL -6.65442
|
186 |
+
▁LE -6.66382
|
187 |
+
▁BEEN -6.67806
|
188 |
+
▁SH -6.67835
|
189 |
+
▁RA -6.68003
|
190 |
+
▁SEE -6.69546
|
191 |
+
KE -6.70826
|
192 |
+
UL -6.71612
|
193 |
+
TED -6.71696
|
194 |
+
▁SA -6.72967
|
195 |
+
UN -6.73177
|
196 |
+
UND -6.73395
|
197 |
+
ANT -6.73423
|
198 |
+
▁NE -6.743
|
199 |
+
IS -6.75404
|
200 |
+
▁THEM -6.75743
|
201 |
+
CI -6.76993
|
202 |
+
GE -6.77069
|
203 |
+
▁COULD -6.77503
|
204 |
+
▁DIS -6.78135
|
205 |
+
OM -6.79366
|
206 |
+
ISH -6.80337
|
207 |
+
HE -6.80705
|
208 |
+
EST -6.81058
|
209 |
+
▁SOME -6.81704
|
210 |
+
ENCE -6.82267
|
211 |
+
ITY -6.83585
|
212 |
+
IVE -6.84022
|
213 |
+
▁US -6.84091
|
214 |
+
▁MORE -6.84456
|
215 |
+
▁EN -6.84947
|
216 |
+
ARD -6.85159
|
217 |
+
ATE -6.86067
|
218 |
+
▁YOUR -6.86188
|
219 |
+
▁INTO -6.86252
|
220 |
+
▁KNOW -6.86753
|
221 |
+
▁CO -6.86961
|
222 |
+
ANCE -6.8727
|
223 |
+
▁TIME -6.8751
|
224 |
+
▁WI -6.88392
|
225 |
+
▁YE -6.8877
|
226 |
+
AGE -6.8955
|
227 |
+
▁NOW -6.90387
|
228 |
+
TI -6.90402
|
229 |
+
FF -6.90618
|
230 |
+
ABLE -6.90917
|
231 |
+
▁VERY -6.92207
|
232 |
+
▁LIKE -6.92869
|
233 |
+
AM -6.94687
|
234 |
+
HI -6.94986
|
235 |
+
Z -6.9511
|
236 |
+
▁OTHER -6.96464
|
237 |
+
▁THAN -6.97308
|
238 |
+
▁LITTLE -6.97622
|
239 |
+
▁DID -6.98152
|
240 |
+
▁LOOK -6.98467
|
241 |
+
TY -6.99474
|
242 |
+
ERS -6.99918
|
243 |
+
▁CAN -7.00994
|
244 |
+
▁CHA -7.01063
|
245 |
+
▁AR -7.02555
|
246 |
+
X -7.02668
|
247 |
+
FUL -7.03465
|
248 |
+
UGH -7.04608
|
249 |
+
▁BA -7.04937
|
250 |
+
▁DAY -7.0543
|
251 |
+
▁ABOUT -7.05554
|
252 |
+
TEN -7.05588
|
253 |
+
IM -7.0583
|
254 |
+
▁ANY -7.05892
|
255 |
+
▁PRE -7.06131
|
256 |
+
▁OVER -7.06494
|
257 |
+
IES -7.07832
|
258 |
+
NESS -7.08111
|
259 |
+
ME -7.08369
|
260 |
+
BLE -7.08645
|
261 |
+
▁M -7.09032
|
262 |
+
ROW -7.09219
|
263 |
+
▁HAS -7.0976
|
264 |
+
▁GREAT -7.10444
|
265 |
+
▁VI -7.10527
|
266 |
+
TA -7.10781
|
267 |
+
▁AFTER -7.10952
|
268 |
+
PER -7.1132
|
269 |
+
▁AGAIN -7.11478
|
270 |
+
HO -7.11545
|
271 |
+
SH -7.11555
|
272 |
+
▁UPON -7.12675
|
273 |
+
▁DI -7.13004
|
274 |
+
▁HAND -7.13211
|
275 |
+
▁COM -7.13273
|
276 |
+
IST -7.13438
|
277 |
+
TURE -7.13771
|
278 |
+
▁STA -7.14628
|
279 |
+
▁THEN -7.15775
|
280 |
+
▁SHOULD -7.15836
|
281 |
+
▁GA -7.16774
|
282 |
+
OUS -7.16944
|
283 |
+
OUR -7.16965
|
284 |
+
▁WELL -7.17122
|
285 |
+
▁ONLY -7.17628
|
286 |
+
MAN -7.17899
|
287 |
+
▁GOOD -7.18494
|
288 |
+
▁TWO -7.18746
|
289 |
+
▁MAR -7.18755
|
290 |
+
▁SAY -7.19636
|
291 |
+
▁HU -7.20214
|
292 |
+
TING -7.20818
|
293 |
+
▁OUR -7.21813
|
294 |
+
RESS -7.22296
|
295 |
+
▁DOWN -7.22319
|
296 |
+
IOUS -7.24748
|
297 |
+
▁BEFORE -7.24835
|
298 |
+
▁DA -7.2508
|
299 |
+
▁NA -7.25861
|
300 |
+
QUI -7.26388
|
301 |
+
▁MADE -7.26918
|
302 |
+
▁EVERY -7.26921
|
303 |
+
▁OLD -7.27794
|
304 |
+
▁EVEN -7.28005
|
305 |
+
IG -7.28081
|
306 |
+
▁COME -7.28172
|
307 |
+
▁GRA -7.28522
|
308 |
+
▁RI -7.29145
|
309 |
+
▁LONG -7.29314
|
310 |
+
OT -7.29691
|
311 |
+
SIDE -7.30065
|
312 |
+
WARD -7.31155
|
313 |
+
▁FO -7.31391
|
314 |
+
▁WHERE -7.31479
|
315 |
+
MO -7.31992
|
316 |
+
LESS -7.32883
|
317 |
+
▁SC -7.32891
|
318 |
+
▁MUST -7.3305
|
319 |
+
▁NEVER -7.33078
|
320 |
+
▁HOW -7.34345
|
321 |
+
▁CAME -7.34599
|
322 |
+
▁SUCH -7.34721
|
323 |
+
▁RU -7.35962
|
324 |
+
▁TAKE -7.35962
|
325 |
+
▁WO -7.36853
|
326 |
+
▁CAR -7.37945
|
327 |
+
UM -7.37964
|
328 |
+
AK -7.39205
|
329 |
+
▁THINK -7.40939
|
330 |
+
▁MUCH -7.40963
|
331 |
+
▁MISTER -7.4201
|
332 |
+
▁MAY -7.43389
|
333 |
+
▁JO -7.44387
|
334 |
+
▁WAY -7.4456
|
335 |
+
▁COMP -7.45547
|
336 |
+
▁THOUGHT -7.45606
|
337 |
+
▁STO -7.46284
|
338 |
+
▁MEN -7.46377
|
339 |
+
▁BACK -7.46526
|
340 |
+
▁DON -7.46548
|
341 |
+
J -7.46605
|
342 |
+
▁LET -7.48391
|
343 |
+
▁TRA -7.4958
|
344 |
+
▁FIRST -7.49608
|
345 |
+
▁JUST -7.49723
|
346 |
+
▁VA -7.49963
|
347 |
+
▁OWN -7.51114
|
348 |
+
▁PLA -7.51664
|
349 |
+
▁MAKE -7.5218
|
350 |
+
ATED -7.52921
|
351 |
+
▁HIMSELF -7.53339
|
352 |
+
▁WENT -7.54
|
353 |
+
▁PI -7.55717
|
354 |
+
GG -7.55994
|
355 |
+
RING -7.5606
|
356 |
+
▁DU -7.56341
|
357 |
+
▁MIGHT -7.56862
|
358 |
+
▁PART -7.57009
|
359 |
+
▁GIVE -7.58394
|
360 |
+
▁IMP -7.58817
|
361 |
+
▁BU -7.59192
|
362 |
+
▁PER -7.59583
|
363 |
+
▁PLACE -7.60502
|
364 |
+
▁HOUSE -7.60934
|
365 |
+
▁THROUGH -7.62521
|
366 |
+
IAN -7.62855
|
367 |
+
▁SW -7.63782
|
368 |
+
▁UNDER -7.64373
|
369 |
+
QUE -7.64402
|
370 |
+
▁AWAY -7.64512
|
371 |
+
▁LOVE -7.64681
|
372 |
+
QUA -7.65031
|
373 |
+
▁LIFE -7.66029
|
374 |
+
▁GET -7.66648
|
375 |
+
▁WITHOUT -7.67412
|
376 |
+
▁PASS -7.682
|
377 |
+
▁TURN -7.69236
|
378 |
+
IGN -7.69649
|
379 |
+
▁HEAD -7.69697
|
380 |
+
▁MOST -7.70515
|
381 |
+
▁THOSE -7.7168
|
382 |
+
▁SHALL -7.71795
|
383 |
+
▁EYES -7.71861
|
384 |
+
▁COL -7.74121
|
385 |
+
▁STILL -7.74208
|
386 |
+
▁NIGHT -7.74542
|
387 |
+
▁NOTHING -7.76816
|
388 |
+
ITION -7.76824
|
389 |
+
HA -7.76993
|
390 |
+
▁TELL -7.76996
|
391 |
+
▁WORK -7.77374
|
392 |
+
▁LAST -7.77545
|
393 |
+
▁NEW -7.78277
|
394 |
+
▁FACE -7.78386
|
395 |
+
▁HI -7.79126
|
396 |
+
▁WORD -7.8012
|
397 |
+
▁FOUND -7.80479
|
398 |
+
▁COUNT -7.80516
|
399 |
+
▁OB -7.80527
|
400 |
+
▁WHILE -7.80765
|
401 |
+
▁SHA -7.81719
|
402 |
+
▁MEAN -7.83619
|
403 |
+
▁SAW -7.83676
|
404 |
+
▁PEOPLE -7.83766
|
405 |
+
▁FRIEND -7.8565
|
406 |
+
▁THREE -7.86814
|
407 |
+
▁ROOM -7.87585
|
408 |
+
▁SAME -7.88751
|
409 |
+
▁THOUGH -7.89248
|
410 |
+
▁RIGHT -7.89619
|
411 |
+
▁CHILD -7.89778
|
412 |
+
▁FATHER -7.90382
|
413 |
+
▁ANOTHER -7.90587
|
414 |
+
▁HEART -7.91276
|
415 |
+
▁WANT -7.92235
|
416 |
+
▁TOOK -7.94253
|
417 |
+
OOK -7.94851
|
418 |
+
▁LIGHT -7.96145
|
419 |
+
▁MISSUS -7.9786
|
420 |
+
▁OPEN -7.98527
|
421 |
+
▁JU -7.9894
|
422 |
+
▁ASKED -7.99096
|
423 |
+
PORT -8.0012
|
424 |
+
▁LEFT -8.00187
|
425 |
+
▁JA -8.02979
|
426 |
+
▁WORLD -8.03992
|
427 |
+
▁HOME -8.04939
|
428 |
+
▁WHY -8.0618
|
429 |
+
▁ALWAYS -8.06564
|
430 |
+
▁ANSWER -8.0739
|
431 |
+
▁SEEMED -8.088
|
432 |
+
▁SOMETHING -8.08951
|
433 |
+
▁GIRL -8.09335
|
434 |
+
▁BECAUSE -8.10615
|
435 |
+
▁NAME -8.10768
|
436 |
+
▁TOLD -8.11746
|
437 |
+
▁NI -8.12176
|
438 |
+
▁HIGH -8.12178
|
439 |
+
IZE -8.13805
|
440 |
+
▁WOMAN -8.14522
|
441 |
+
▁FOLLOW -8.15124
|
442 |
+
▁RETURN -8.17126
|
443 |
+
▁KNEW -8.17579
|
444 |
+
▁EACH -8.18032
|
445 |
+
▁KIND -8.18787
|
446 |
+
▁JE -8.19007
|
447 |
+
▁ACT -8.20004
|
448 |
+
▁LU -8.20535
|
449 |
+
▁CERTAIN -8.21049
|
450 |
+
▁YEARS -8.2275
|
451 |
+
▁QUITE -8.22848
|
452 |
+
▁APPEAR -8.23444
|
453 |
+
▁BETTER -8.24887
|
454 |
+
▁HALF -8.25101
|
455 |
+
▁PRESENT -8.25108
|
456 |
+
▁PRINCE -8.263
|
457 |
+
SHIP -8.26654
|
458 |
+
▁ALSO -8.27005
|
459 |
+
▁BEGAN -8.27496
|
460 |
+
▁HAVING -8.28474
|
461 |
+
▁ENOUGH -8.28608
|
462 |
+
▁PERSON -8.28836
|
463 |
+
▁LADY -8.29498
|
464 |
+
▁WHITE -8.3115
|
465 |
+
▁COURSE -8.31653
|
466 |
+
▁VOICE -8.3193
|
467 |
+
▁SPEAK -8.32799
|
468 |
+
▁POWER -8.35211
|
469 |
+
▁MORNING -8.35582
|
470 |
+
▁BETWEEN -8.3565
|
471 |
+
▁AMONG -8.35997
|
472 |
+
▁KEEP -8.36216
|
473 |
+
▁WALK -8.3686
|
474 |
+
▁MATTER -8.37061
|
475 |
+
▁TEA -8.37863
|
476 |
+
▁BELIEVE -8.37922
|
477 |
+
▁SMALL -8.3814
|
478 |
+
▁TALK -8.38939
|
479 |
+
▁FELT -8.39477
|
480 |
+
▁HORSE -8.39834
|
481 |
+
▁MYSELF -8.40051
|
482 |
+
▁SIX -8.40069
|
483 |
+
▁HOWEVER -8.40304
|
484 |
+
▁FULL -8.40399
|
485 |
+
▁HERSELF -8.40714
|
486 |
+
▁POINT -8.41248
|
487 |
+
▁STOOD -8.41336
|
488 |
+
▁HUNDRED -8.41404
|
489 |
+
▁ALMOST -8.42802
|
490 |
+
▁SINCE -8.43626
|
491 |
+
▁LARGE -8.44207
|
492 |
+
▁LEAVE -8.44699
|
493 |
+
▁PERHAPS -8.4576
|
494 |
+
▁DARK -8.46885
|
495 |
+
▁SUDDEN -8.46906
|
496 |
+
▁REPLIED -8.47536
|
497 |
+
▁ANYTHING -8.48241
|
498 |
+
▁WONDER -8.48792
|
499 |
+
▁UNTIL -8.48926
|
500 |
+
Q -9.78832
|
data/lang_bpe_500/words.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|