Upload tokenizer
Browse files- added_tokens.json +109 -0
- merges.txt +447 -0
- special_tokens_map.json +115 -0
- tokenizer_config.json +978 -0
- vocab.json +502 -0
added_tokens.json
ADDED
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|af|>": 570,
|
3 |
+
"<|am|>": 577,
|
4 |
+
"<|ar|>": 515,
|
5 |
+
"<|as|>": 593,
|
6 |
+
"<|az|>": 547,
|
7 |
+
"<|ba|>": 598,
|
8 |
+
"<|be|>": 573,
|
9 |
+
"<|bg|>": 535,
|
10 |
+
"<|bn|>": 545,
|
11 |
+
"<|bo|>": 590,
|
12 |
+
"<|br|>": 552,
|
13 |
+
"<|bs|>": 558,
|
14 |
+
"<|ca|>": 513,
|
15 |
+
"<|cs|>": 526,
|
16 |
+
"<|cy|>": 540,
|
17 |
+
"<|da|>": 528,
|
18 |
+
"<|de|>": 504,
|
19 |
+
"<|el|>": 524,
|
20 |
+
"<|endoftext|>": 500,
|
21 |
+
"<|en|>": 502,
|
22 |
+
"<|es|>": 505,
|
23 |
+
"<|et|>": 550,
|
24 |
+
"<|eu|>": 553,
|
25 |
+
"<|fa|>": 543,
|
26 |
+
"<|fi|>": 520,
|
27 |
+
"<|fo|>": 581,
|
28 |
+
"<|fr|>": 508,
|
29 |
+
"<|gl|>": 562,
|
30 |
+
"<|gu|>": 576,
|
31 |
+
"<|haw|>": 595,
|
32 |
+
"<|ha|>": 597,
|
33 |
+
"<|he|>": 522,
|
34 |
+
"<|hi|>": 519,
|
35 |
+
"<|hr|>": 534,
|
36 |
+
"<|ht|>": 582,
|
37 |
+
"<|hu|>": 529,
|
38 |
+
"<|hy|>": 555,
|
39 |
+
"<|id|>": 518,
|
40 |
+
"<|is|>": 554,
|
41 |
+
"<|it|>": 517,
|
42 |
+
"<|ja|>": 509,
|
43 |
+
"<|jw|>": 599,
|
44 |
+
"<|ka|>": 572,
|
45 |
+
"<|kk|>": 559,
|
46 |
+
"<|km|>": 566,
|
47 |
+
"<|kn|>": 549,
|
48 |
+
"<|ko|>": 507,
|
49 |
+
"<|la|>": 537,
|
50 |
+
"<|lb|>": 588,
|
51 |
+
"<|ln|>": 596,
|
52 |
+
"<|lo|>": 579,
|
53 |
+
"<|lt|>": 536,
|
54 |
+
"<|lv|>": 544,
|
55 |
+
"<|mg|>": 592,
|
56 |
+
"<|mi|>": 538,
|
57 |
+
"<|mk|>": 551,
|
58 |
+
"<|ml|>": 539,
|
59 |
+
"<|mn|>": 557,
|
60 |
+
"<|mr|>": 563,
|
61 |
+
"<|ms|>": 525,
|
62 |
+
"<|mt|>": 586,
|
63 |
+
"<|my|>": 589,
|
64 |
+
"<|ne|>": 556,
|
65 |
+
"<|nl|>": 514,
|
66 |
+
"<|nn|>": 585,
|
67 |
+
"<|nocaptions|>": 605,
|
68 |
+
"<|notimestamps|>": 606,
|
69 |
+
"<|no|>": 531,
|
70 |
+
"<|oc|>": 571,
|
71 |
+
"<|pa|>": 564,
|
72 |
+
"<|pl|>": 512,
|
73 |
+
"<|ps|>": 583,
|
74 |
+
"<|pt|>": 510,
|
75 |
+
"<|ro|>": 527,
|
76 |
+
"<|ru|>": 506,
|
77 |
+
"<|sa|>": 587,
|
78 |
+
"<|sd|>": 575,
|
79 |
+
"<|si|>": 565,
|
80 |
+
"<|sk|>": 541,
|
81 |
+
"<|sl|>": 548,
|
82 |
+
"<|sn|>": 567,
|
83 |
+
"<|so|>": 569,
|
84 |
+
"<|sq|>": 560,
|
85 |
+
"<|sr|>": 546,
|
86 |
+
"<|startoflm|>": 603,
|
87 |
+
"<|startofprev|>": 604,
|
88 |
+
"<|startoftranscript|>": 501,
|
89 |
+
"<|su|>": 600,
|
90 |
+
"<|sv|>": 516,
|
91 |
+
"<|sw|>": 561,
|
92 |
+
"<|ta|>": 530,
|
93 |
+
"<|te|>": 542,
|
94 |
+
"<|tg|>": 574,
|
95 |
+
"<|th|>": 532,
|
96 |
+
"<|tk|>": 584,
|
97 |
+
"<|tl|>": 591,
|
98 |
+
"<|transcribe|>": 602,
|
99 |
+
"<|translate|>": 601,
|
100 |
+
"<|tr|>": 511,
|
101 |
+
"<|tt|>": 594,
|
102 |
+
"<|uk|>": 523,
|
103 |
+
"<|ur|>": 533,
|
104 |
+
"<|uz|>": 580,
|
105 |
+
"<|vi|>": 521,
|
106 |
+
"<|yi|>": 578,
|
107 |
+
"<|yo|>": 568,
|
108 |
+
"<|zh|>": 503
|
109 |
+
}
|
merges.txt
ADDED
@@ -0,0 +1,447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#version: 0.2
|
2 |
+
č Ċ
|
3 |
+
Ġ čĊ
|
4 |
+
5 3
|
5 |
+
1 1
|
6 |
+
4 53
|
7 |
+
53 3
|
8 |
+
4 2
|
9 |
+
Ç ¾
|
10 |
+
2 4
|
11 |
+
2 1
|
12 |
+
É Ķ
|
13 |
+
Å ĭ
|
14 |
+
t s
|
15 |
+
É ¬
|
16 |
+
Ġ Ǿ
|
17 |
+
a i
|
18 |
+
Ġ l
|
19 |
+
Ġ k
|
20 |
+
ÉĶ u
|
21 |
+
h u
|
22 |
+
É Ĵ
|
23 |
+
Ê Ķ
|
24 |
+
1 3
|
25 |
+
a u
|
26 |
+
u a
|
27 |
+
Ġ n
|
28 |
+
Ġ ɬ
|
29 |
+
ts h
|
30 |
+
É ¤
|
31 |
+
i a
|
32 |
+
i Åĭ
|
33 |
+
É ¯
|
34 |
+
ɤ ɯ
|
35 |
+
k h
|
36 |
+
Ġ m
|
37 |
+
Ġ t
|
38 |
+
Ġ ts
|
39 |
+
p u
|
40 |
+
5 5
|
41 |
+
a Åĭ
|
42 |
+
u i
|
43 |
+
i e
|
44 |
+
Ġ p
|
45 |
+
i u
|
46 |
+
o u
|
47 |
+
É Ľ
|
48 |
+
o i
|
49 |
+
à ¸
|
50 |
+
ie u
|
51 |
+
t h
|
52 |
+
Ġl i
|
53 |
+
hu a
|
54 |
+
Ì ĥ
|
55 |
+
k e
|
56 |
+
k u
|
57 |
+
Ġ h
|
58 |
+
4 1
|
59 |
+
Ġl au
|
60 |
+
4 42
|
61 |
+
p h
|
62 |
+
ĠǾ i
|
63 |
+
ĠǾ u
|
64 |
+
e ÊĶ
|
65 |
+
ÉĶ Åĭ
|
66 |
+
e Åĭ
|
67 |
+
i ÊĶ
|
68 |
+
p e
|
69 |
+
Ġk h
|
70 |
+
ÉĶ ÊĶ
|
71 |
+
4 4
|
72 |
+
5 44
|
73 |
+
ɬ ia
|
74 |
+
Ġm a
|
75 |
+
Ġ Åĭ
|
76 |
+
Ġn iÅĭ
|
77 |
+
hu ai
|
78 |
+
k y
|
79 |
+
p ai
|
80 |
+
hu e
|
81 |
+
hu ɤɯ
|
82 |
+
hu oi
|
83 |
+
h ÉĶu
|
84 |
+
i au
|
85 |
+
Ġ tsh
|
86 |
+
ĠǾ au
|
87 |
+
t y
|
88 |
+
t ua
|
89 |
+
à £
|
90 |
+
h y
|
91 |
+
k ua
|
92 |
+
t ÉĶu
|
93 |
+
l i
|
94 |
+
Ǿ e
|
95 |
+
hu i
|
96 |
+
Ġp h
|
97 |
+
ĠǾ ua
|
98 |
+
Ġn i
|
99 |
+
Ġɬ e
|
100 |
+
kh e
|
101 |
+
t e
|
102 |
+
ĠǾ ÉĴ
|
103 |
+
Ġk u
|
104 |
+
Ǿ ia
|
105 |
+
Ġn au
|
106 |
+
ã Ģ
|
107 |
+
Ġ ãĢ
|
108 |
+
ĠǾ a
|
109 |
+
Ġk ai
|
110 |
+
ĠãĢ Ĥ
|
111 |
+
i n
|
112 |
+
Ġl e
|
113 |
+
Ġl ui
|
114 |
+
Ġk ÉĶ
|
115 |
+
Ġɬ y
|
116 |
+
2 3
|
117 |
+
t i
|
118 |
+
Ǿ ÉĶu
|
119 |
+
Ġl ai
|
120 |
+
Ġk ÉĴ
|
121 |
+
ÉĽ u
|
122 |
+
ĠǾ y
|
123 |
+
kh ÉĶu
|
124 |
+
h e
|
125 |
+
k ÉĴ
|
126 |
+
Ġk a
|
127 |
+
Ġts y
|
128 |
+
o Åĭ
|
129 |
+
ɬ e
|
130 |
+
ɬ i
|
131 |
+
ɬ y
|
132 |
+
ɬ ua
|
133 |
+
ɬ ø
|
134 |
+
ÉĴ ÊĶ
|
135 |
+
Ġɬ i
|
136 |
+
Ġts i
|
137 |
+
pu e
|
138 |
+
pu ɤɯ
|
139 |
+
h ai
|
140 |
+
k ai
|
141 |
+
p ÉĶu
|
142 |
+
ts ia
|
143 |
+
Ġl ÉĽ
|
144 |
+
Ġt e
|
145 |
+
pu ai
|
146 |
+
pu oi
|
147 |
+
ph ÉĶu
|
148 |
+
a ÊĶ
|
149 |
+
p i
|
150 |
+
u ai
|
151 |
+
ts y
|
152 |
+
h i
|
153 |
+
k i
|
154 |
+
p ÉĴ
|
155 |
+
ï ¼
|
156 |
+
Ġ ï¼
|
157 |
+
Ǿ ua
|
158 |
+
ts ui
|
159 |
+
ĠǾ aÅĭ
|
160 |
+
Ġk ua
|
161 |
+
tsh y
|
162 |
+
Ġt ai
|
163 |
+
m a
|
164 |
+
u e
|
165 |
+
Î ²
|
166 |
+
Ġ β
|
167 |
+
Ǿ ÉĶ
|
168 |
+
Ǿ ÉĴ
|
169 |
+
ɬ o
|
170 |
+
ɤ Åĭ
|
171 |
+
kh ÉĴ
|
172 |
+
Ġp o
|
173 |
+
Ġli ÊĶ
|
174 |
+
h ÉĴ
|
175 |
+
k ÉĶ
|
176 |
+
k ÉĶu
|
177 |
+
k ieu
|
178 |
+
ts o
|
179 |
+
ĠǾ iu
|
180 |
+
ĠǾ ÉĽ
|
181 |
+
Ġl eÊĶ
|
182 |
+
Ġɬ ia
|
183 |
+
tsh i
|
184 |
+
tsh ai
|
185 |
+
kh y
|
186 |
+
ie Åĭ
|
187 |
+
k o
|
188 |
+
l e
|
189 |
+
l ÉĶu
|
190 |
+
p iÅĭ
|
191 |
+
Ä ©
|
192 |
+
Ǿ i
|
193 |
+
Ǿ au
|
194 |
+
Ǿ iu
|
195 |
+
ɬ u
|
196 |
+
ĠǾ ÉĶu
|
197 |
+
kh i
|
198 |
+
Ġh a
|
199 |
+
Ġh ÉĴ
|
200 |
+
h o
|
201 |
+
l o
|
202 |
+
l ui
|
203 |
+
p a
|
204 |
+
p o
|
205 |
+
p ÉĶ
|
206 |
+
Ǿ aÅĭ
|
207 |
+
ts ÉĶu
|
208 |
+
ĠǾ e
|
209 |
+
tsh iu
|
210 |
+
Ġm ai
|
211 |
+
Ġts ia
|
212 |
+
ÉĽ Åĭ
|
213 |
+
h ÉĶ
|
214 |
+
p ua
|
215 |
+
t hua
|
216 |
+
u ɤɯ
|
217 |
+
u oi
|
218 |
+
ts e
|
219 |
+
ts i
|
220 |
+
ĠǾ iÅĭ
|
221 |
+
Ġk o
|
222 |
+
Ġk au
|
223 |
+
Ġm i
|
224 |
+
th ÉĶu
|
225 |
+
Ġï¼ Ł
|
226 |
+
h ou
|
227 |
+
n i
|
228 |
+
t a
|
229 |
+
Å ©
|
230 |
+
ɬ ieu
|
231 |
+
ĠǾ ÉĶÅĭ
|
232 |
+
Ġk y
|
233 |
+
Ġk ÉĶu
|
234 |
+
Ġn ui
|
235 |
+
Ġɬ ÉĶu
|
236 |
+
Ġɬ iÊĶ
|
237 |
+
Ġm ua
|
238 |
+
Ġt eÅĭ
|
239 |
+
th i
|
240 |
+
th ai
|
241 |
+
l y
|
242 |
+
t ou
|
243 |
+
t ø
|
244 |
+
Åĭ ÉĶu
|
245 |
+
ts ieu
|
246 |
+
ɬ ai
|
247 |
+
Ġl aÅĭ
|
248 |
+
Ġl iu
|
249 |
+
tsh ia
|
250 |
+
ɤ ÊĶ
|
251 |
+
kh ÉĶ
|
252 |
+
Ġp ai
|
253 |
+
ku e
|
254 |
+
ku ɤɯ
|
255 |
+
ku oi
|
256 |
+
Ġh ÉĶ
|
257 |
+
Ġkh ai
|
258 |
+
ĠǾÉĴ Åĭ
|
259 |
+
h a
|
260 |
+
k hui
|
261 |
+
k aÊĶ
|
262 |
+
m iÅĭ
|
263 |
+
p hua
|
264 |
+
t o
|
265 |
+
t ai
|
266 |
+
t ui
|
267 |
+
t hui
|
268 |
+
Ǿ ai
|
269 |
+
Ǿ ou
|
270 |
+
ts ai
|
271 |
+
ts hui
|
272 |
+
ɬ iau
|
273 |
+
ĠǾ ia
|
274 |
+
Ġl o
|
275 |
+
Ġk i
|
276 |
+
Ġk eÊĶ
|
277 |
+
Ġn ai
|
278 |
+
Ġɬ a
|
279 |
+
tsh ø
|
280 |
+
Ġm ÉĴ
|
281 |
+
Ġt he
|
282 |
+
th iu
|
283 |
+
ku ai
|
284 |
+
ph ai
|
285 |
+
ph aÅĭ
|
286 |
+
ĠǾu ai
|
287 |
+
Ġkh i
|
288 |
+
ĠÅĭ ua
|
289 |
+
Ġtsh y
|
290 |
+
Ġph i
|
291 |
+
k iÅĭ
|
292 |
+
t ÉĴ
|
293 |
+
t iu
|
294 |
+
ɬ aÅĭ
|
295 |
+
ĠǾ ÉĶ
|
296 |
+
ĠǾ ou
|
297 |
+
Ġl y
|
298 |
+
Ġn e
|
299 |
+
Ġn u
|
300 |
+
Ġɬ ieu
|
301 |
+
tsh a
|
302 |
+
Ġts e
|
303 |
+
Ġts ui
|
304 |
+
Ġp ɤɯ
|
305 |
+
ĠǾu e
|
306 |
+
ĠǾu oi
|
307 |
+
ĠÅĭ iÅĭ
|
308 |
+
Ġku ɤɯ
|
309 |
+
ĠlÉĽ ÊĶ
|
310 |
+
k ø
|
311 |
+
k in
|
312 |
+
l ÉĴ
|
313 |
+
l iÊĶ
|
314 |
+
m ÉĴ
|
315 |
+
n ÉĶu
|
316 |
+
p ou
|
317 |
+
p huai
|
318 |
+
p hue
|
319 |
+
p huɤɯ
|
320 |
+
p huoi
|
321 |
+
t ÉĶ
|
322 |
+
Å ĵ
|
323 |
+
Ġ pu
|
324 |
+
Ǿ y
|
325 |
+
ɬ ÉĶu
|
326 |
+
ĠǾ o
|
327 |
+
Ġl ÉĴ
|
328 |
+
Ġl ia
|
329 |
+
Ġk hu
|
330 |
+
Ġk aÅĭ
|
331 |
+
Ġk ÉĶÅĭ
|
332 |
+
Ġn ÉĴ
|
333 |
+
Ġn aÅĭ
|
334 |
+
Ġn ø
|
335 |
+
Ġn ieu
|
336 |
+
Ġɬ ÉĶ
|
337 |
+
tsh ÉĶ
|
338 |
+
tsh ÉĴ
|
339 |
+
tsh ÉĴÊĶ
|
340 |
+
kh ou
|
341 |
+
Ġm iÅĭ
|
342 |
+
Ġt i
|
343 |
+
Ġt ÉĴ
|
344 |
+
Ġt au
|
345 |
+
Ġts ÉĶ
|
346 |
+
Ġts eÊĶ
|
347 |
+
Ġp ÉĶÊĶ
|
348 |
+
ÉĽ n
|
349 |
+
th y
|
350 |
+
th iÅĭ
|
351 |
+
ph ou
|
352 |
+
ĠÅĭ ÉĶu
|
353 |
+
hy ÉĴ
|
354 |
+
h ia
|
355 |
+
i Å©
|
356 |
+
k ɤɯ
|
357 |
+
k iau
|
358 |
+
l ø
|
359 |
+
p ɤɯ
|
360 |
+
Ġ hu
|
361 |
+
Ǿ o
|
362 |
+
Ǿ u
|
363 |
+
Ǿ iÅĭ
|
364 |
+
ts ɤɯ
|
365 |
+
ɬ iu
|
366 |
+
ɬ ÉĶÊĶ
|
367 |
+
ĠǾ eÊĶ
|
368 |
+
Ġl eÅĭ
|
369 |
+
Ġk ia
|
370 |
+
Ġn y
|
371 |
+
Ġɬ u
|
372 |
+
Ġɬ ÉĴ
|
373 |
+
tsh au
|
374 |
+
tsh eÅĭ
|
375 |
+
kh ieu
|
376 |
+
Ġm ÉĶ
|
377 |
+
Ġm ia
|
378 |
+
Ġm uai
|
379 |
+
Ġt y
|
380 |
+
Ġts ieu
|
381 |
+
ie ÊĶ
|
382 |
+
ø Åĭ
|
383 |
+
Ġh iÅ©
|
384 |
+
ĠǾi ÊĶ
|
385 |
+
ĠǾi au
|
386 |
+
ĠǾu ã
|
387 |
+
hy a
|
388 |
+
hy ÉĶ
|
389 |
+
Ġku ai
|
390 |
+
ĠǾy Åĭ
|
391 |
+
ki ÉĽu
|
392 |
+
Ġï¼ Į
|
393 |
+
ĠÇ¾ÉĽ ÊĶ
|
394 |
+
Ġko ÊĶ
|
395 |
+
a m
|
396 |
+
a n
|
397 |
+
a kieu
|
398 |
+
k ou
|
399 |
+
k hue
|
400 |
+
k huɤɯ
|
401 |
+
l ÉĶ
|
402 |
+
l ua
|
403 |
+
l ɤɯ
|
404 |
+
l iu
|
405 |
+
l ou
|
406 |
+
m ÉĶ
|
407 |
+
m ui
|
408 |
+
m in
|
409 |
+
n iÅĭ
|
410 |
+
o n
|
411 |
+
p au
|
412 |
+
p ÉĽ
|
413 |
+
p eÊĶ
|
414 |
+
t iÅĭ
|
415 |
+
t eÅĭ
|
416 |
+
Ġ hua
|
417 |
+
ts ÉĶ
|
418 |
+
ts ÉĴ
|
419 |
+
ts ou
|
420 |
+
ts iau
|
421 |
+
ɬ iÊĶ
|
422 |
+
Ġl ua
|
423 |
+
Ġk iÅĭ
|
424 |
+
Ġk hua
|
425 |
+
Ġn ÉĶ
|
426 |
+
Ġn ua
|
427 |
+
Ġn ÉĶÅĭ
|
428 |
+
Ġɬ o
|
429 |
+
Ġɬ ui
|
430 |
+
Ġɬ ÉĶÊĶ
|
431 |
+
tsh aÅĭ
|
432 |
+
kh a
|
433 |
+
Ġm e
|
434 |
+
Ġm ue
|
435 |
+
Ġt h
|
436 |
+
Ġt ÉĶ
|
437 |
+
Ġt ua
|
438 |
+
Ġt ui
|
439 |
+
Ġts ÉĴ
|
440 |
+
Ġts iÅĭ
|
441 |
+
Ġts iÊĶ
|
442 |
+
Ġts ÉĴÊĶ
|
443 |
+
Ġp iÊĶ
|
444 |
+
ø n
|
445 |
+
ø ÊĶ
|
446 |
+
th au
|
447 |
+
th aÅĭ
|
special_tokens_map.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|endoftext|>",
|
4 |
+
"<|startoftranscript|>",
|
5 |
+
"<|en|>",
|
6 |
+
"<|zh|>",
|
7 |
+
"<|de|>",
|
8 |
+
"<|es|>",
|
9 |
+
"<|ru|>",
|
10 |
+
"<|ko|>",
|
11 |
+
"<|fr|>",
|
12 |
+
"<|ja|>",
|
13 |
+
"<|pt|>",
|
14 |
+
"<|tr|>",
|
15 |
+
"<|pl|>",
|
16 |
+
"<|ca|>",
|
17 |
+
"<|nl|>",
|
18 |
+
"<|ar|>",
|
19 |
+
"<|sv|>",
|
20 |
+
"<|it|>",
|
21 |
+
"<|id|>",
|
22 |
+
"<|hi|>",
|
23 |
+
"<|fi|>",
|
24 |
+
"<|vi|>",
|
25 |
+
"<|he|>",
|
26 |
+
"<|uk|>",
|
27 |
+
"<|el|>",
|
28 |
+
"<|ms|>",
|
29 |
+
"<|cs|>",
|
30 |
+
"<|ro|>",
|
31 |
+
"<|da|>",
|
32 |
+
"<|hu|>",
|
33 |
+
"<|ta|>",
|
34 |
+
"<|no|>",
|
35 |
+
"<|th|>",
|
36 |
+
"<|ur|>",
|
37 |
+
"<|hr|>",
|
38 |
+
"<|bg|>",
|
39 |
+
"<|lt|>",
|
40 |
+
"<|la|>",
|
41 |
+
"<|mi|>",
|
42 |
+
"<|ml|>",
|
43 |
+
"<|cy|>",
|
44 |
+
"<|sk|>",
|
45 |
+
"<|te|>",
|
46 |
+
"<|fa|>",
|
47 |
+
"<|lv|>",
|
48 |
+
"<|bn|>",
|
49 |
+
"<|sr|>",
|
50 |
+
"<|az|>",
|
51 |
+
"<|sl|>",
|
52 |
+
"<|kn|>",
|
53 |
+
"<|et|>",
|
54 |
+
"<|mk|>",
|
55 |
+
"<|br|>",
|
56 |
+
"<|eu|>",
|
57 |
+
"<|is|>",
|
58 |
+
"<|hy|>",
|
59 |
+
"<|ne|>",
|
60 |
+
"<|mn|>",
|
61 |
+
"<|bs|>",
|
62 |
+
"<|kk|>",
|
63 |
+
"<|sq|>",
|
64 |
+
"<|sw|>",
|
65 |
+
"<|gl|>",
|
66 |
+
"<|mr|>",
|
67 |
+
"<|pa|>",
|
68 |
+
"<|si|>",
|
69 |
+
"<|km|>",
|
70 |
+
"<|sn|>",
|
71 |
+
"<|yo|>",
|
72 |
+
"<|so|>",
|
73 |
+
"<|af|>",
|
74 |
+
"<|oc|>",
|
75 |
+
"<|ka|>",
|
76 |
+
"<|be|>",
|
77 |
+
"<|tg|>",
|
78 |
+
"<|sd|>",
|
79 |
+
"<|gu|>",
|
80 |
+
"<|am|>",
|
81 |
+
"<|yi|>",
|
82 |
+
"<|lo|>",
|
83 |
+
"<|uz|>",
|
84 |
+
"<|fo|>",
|
85 |
+
"<|ht|>",
|
86 |
+
"<|ps|>",
|
87 |
+
"<|tk|>",
|
88 |
+
"<|nn|>",
|
89 |
+
"<|mt|>",
|
90 |
+
"<|sa|>",
|
91 |
+
"<|lb|>",
|
92 |
+
"<|my|>",
|
93 |
+
"<|bo|>",
|
94 |
+
"<|tl|>",
|
95 |
+
"<|mg|>",
|
96 |
+
"<|as|>",
|
97 |
+
"<|tt|>",
|
98 |
+
"<|haw|>",
|
99 |
+
"<|ln|>",
|
100 |
+
"<|ha|>",
|
101 |
+
"<|ba|>",
|
102 |
+
"<|jw|>",
|
103 |
+
"<|su|>",
|
104 |
+
"<|translate|>",
|
105 |
+
"<|transcribe|>",
|
106 |
+
"<|startoflm|>",
|
107 |
+
"<|startofprev|>",
|
108 |
+
"<|nocaptions|>",
|
109 |
+
"<|notimestamps|>"
|
110 |
+
],
|
111 |
+
"bos_token": "<|endoftext|>",
|
112 |
+
"eos_token": "<|endoftext|>",
|
113 |
+
"pad_token": "<|endoftext|>",
|
114 |
+
"unk_token": "<|endoftext|>"
|
115 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,978 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"500": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": true,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": true,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"501": {
|
13 |
+
"content": "<|startoftranscript|>",
|
14 |
+
"lstrip": true,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": true,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"502": {
|
21 |
+
"content": "<|en|>",
|
22 |
+
"lstrip": true,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": true,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"503": {
|
29 |
+
"content": "<|zh|>",
|
30 |
+
"lstrip": true,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": true,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"504": {
|
37 |
+
"content": "<|de|>",
|
38 |
+
"lstrip": true,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": true,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"505": {
|
45 |
+
"content": "<|es|>",
|
46 |
+
"lstrip": true,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": true,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"506": {
|
53 |
+
"content": "<|ru|>",
|
54 |
+
"lstrip": true,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": true,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"507": {
|
61 |
+
"content": "<|ko|>",
|
62 |
+
"lstrip": true,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": true,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"508": {
|
69 |
+
"content": "<|fr|>",
|
70 |
+
"lstrip": true,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": true,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"509": {
|
77 |
+
"content": "<|ja|>",
|
78 |
+
"lstrip": true,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": true,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"510": {
|
85 |
+
"content": "<|pt|>",
|
86 |
+
"lstrip": true,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": true,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"511": {
|
93 |
+
"content": "<|tr|>",
|
94 |
+
"lstrip": true,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": true,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"512": {
|
101 |
+
"content": "<|pl|>",
|
102 |
+
"lstrip": true,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": true,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"513": {
|
109 |
+
"content": "<|ca|>",
|
110 |
+
"lstrip": true,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": true,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"514": {
|
117 |
+
"content": "<|nl|>",
|
118 |
+
"lstrip": true,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": true,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"515": {
|
125 |
+
"content": "<|ar|>",
|
126 |
+
"lstrip": true,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": true,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"516": {
|
133 |
+
"content": "<|sv|>",
|
134 |
+
"lstrip": true,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": true,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"517": {
|
141 |
+
"content": "<|it|>",
|
142 |
+
"lstrip": true,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": true,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"518": {
|
149 |
+
"content": "<|id|>",
|
150 |
+
"lstrip": true,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": true,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"519": {
|
157 |
+
"content": "<|hi|>",
|
158 |
+
"lstrip": true,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": true,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"520": {
|
165 |
+
"content": "<|fi|>",
|
166 |
+
"lstrip": true,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": true,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"521": {
|
173 |
+
"content": "<|vi|>",
|
174 |
+
"lstrip": true,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": true,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"522": {
|
181 |
+
"content": "<|he|>",
|
182 |
+
"lstrip": true,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": true,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"523": {
|
189 |
+
"content": "<|uk|>",
|
190 |
+
"lstrip": true,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": true,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"524": {
|
197 |
+
"content": "<|el|>",
|
198 |
+
"lstrip": true,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": true,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"525": {
|
205 |
+
"content": "<|ms|>",
|
206 |
+
"lstrip": true,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": true,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"526": {
|
213 |
+
"content": "<|cs|>",
|
214 |
+
"lstrip": true,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": true,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"527": {
|
221 |
+
"content": "<|ro|>",
|
222 |
+
"lstrip": true,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": true,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"528": {
|
229 |
+
"content": "<|da|>",
|
230 |
+
"lstrip": true,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": true,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"529": {
|
237 |
+
"content": "<|hu|>",
|
238 |
+
"lstrip": true,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": true,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"530": {
|
245 |
+
"content": "<|ta|>",
|
246 |
+
"lstrip": true,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": true,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"531": {
|
253 |
+
"content": "<|no|>",
|
254 |
+
"lstrip": true,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": true,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"532": {
|
261 |
+
"content": "<|th|>",
|
262 |
+
"lstrip": true,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": true,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"533": {
|
269 |
+
"content": "<|ur|>",
|
270 |
+
"lstrip": true,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": true,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"534": {
|
277 |
+
"content": "<|hr|>",
|
278 |
+
"lstrip": true,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": true,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"535": {
|
285 |
+
"content": "<|bg|>",
|
286 |
+
"lstrip": true,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": true,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"536": {
|
293 |
+
"content": "<|lt|>",
|
294 |
+
"lstrip": true,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": true,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"537": {
|
301 |
+
"content": "<|la|>",
|
302 |
+
"lstrip": true,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": true,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"538": {
|
309 |
+
"content": "<|mi|>",
|
310 |
+
"lstrip": true,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": true,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"539": {
|
317 |
+
"content": "<|ml|>",
|
318 |
+
"lstrip": true,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": true,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"540": {
|
325 |
+
"content": "<|cy|>",
|
326 |
+
"lstrip": true,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": true,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"541": {
|
333 |
+
"content": "<|sk|>",
|
334 |
+
"lstrip": true,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": true,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"542": {
|
341 |
+
"content": "<|te|>",
|
342 |
+
"lstrip": true,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": true,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"543": {
|
349 |
+
"content": "<|fa|>",
|
350 |
+
"lstrip": true,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": true,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"544": {
|
357 |
+
"content": "<|lv|>",
|
358 |
+
"lstrip": true,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": true,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"545": {
|
365 |
+
"content": "<|bn|>",
|
366 |
+
"lstrip": true,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": true,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"546": {
|
373 |
+
"content": "<|sr|>",
|
374 |
+
"lstrip": true,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": true,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"547": {
|
381 |
+
"content": "<|az|>",
|
382 |
+
"lstrip": true,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": true,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"548": {
|
389 |
+
"content": "<|sl|>",
|
390 |
+
"lstrip": true,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": true,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"549": {
|
397 |
+
"content": "<|kn|>",
|
398 |
+
"lstrip": true,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": true,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"550": {
|
405 |
+
"content": "<|et|>",
|
406 |
+
"lstrip": true,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": true,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"551": {
|
413 |
+
"content": "<|mk|>",
|
414 |
+
"lstrip": true,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": true,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"552": {
|
421 |
+
"content": "<|br|>",
|
422 |
+
"lstrip": true,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": true,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"553": {
|
429 |
+
"content": "<|eu|>",
|
430 |
+
"lstrip": true,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": true,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"554": {
|
437 |
+
"content": "<|is|>",
|
438 |
+
"lstrip": true,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": true,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"555": {
|
445 |
+
"content": "<|hy|>",
|
446 |
+
"lstrip": true,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": true,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"556": {
|
453 |
+
"content": "<|ne|>",
|
454 |
+
"lstrip": true,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": true,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"557": {
|
461 |
+
"content": "<|mn|>",
|
462 |
+
"lstrip": true,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": true,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"558": {
|
469 |
+
"content": "<|bs|>",
|
470 |
+
"lstrip": true,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": true,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"559": {
|
477 |
+
"content": "<|kk|>",
|
478 |
+
"lstrip": true,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": true,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"560": {
|
485 |
+
"content": "<|sq|>",
|
486 |
+
"lstrip": true,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": true,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"561": {
|
493 |
+
"content": "<|sw|>",
|
494 |
+
"lstrip": true,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": true,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"562": {
|
501 |
+
"content": "<|gl|>",
|
502 |
+
"lstrip": true,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": true,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"563": {
|
509 |
+
"content": "<|mr|>",
|
510 |
+
"lstrip": true,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": true,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"564": {
|
517 |
+
"content": "<|pa|>",
|
518 |
+
"lstrip": true,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": true,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"565": {
|
525 |
+
"content": "<|si|>",
|
526 |
+
"lstrip": true,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": true,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"566": {
|
533 |
+
"content": "<|km|>",
|
534 |
+
"lstrip": true,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": true,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"567": {
|
541 |
+
"content": "<|sn|>",
|
542 |
+
"lstrip": true,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": true,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"568": {
|
549 |
+
"content": "<|yo|>",
|
550 |
+
"lstrip": true,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": true,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"569": {
|
557 |
+
"content": "<|so|>",
|
558 |
+
"lstrip": true,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": true,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"570": {
|
565 |
+
"content": "<|af|>",
|
566 |
+
"lstrip": true,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": true,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"571": {
|
573 |
+
"content": "<|oc|>",
|
574 |
+
"lstrip": true,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": true,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"572": {
|
581 |
+
"content": "<|ka|>",
|
582 |
+
"lstrip": true,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": true,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"573": {
|
589 |
+
"content": "<|be|>",
|
590 |
+
"lstrip": true,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": true,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"574": {
|
597 |
+
"content": "<|tg|>",
|
598 |
+
"lstrip": true,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": true,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"575": {
|
605 |
+
"content": "<|sd|>",
|
606 |
+
"lstrip": true,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": true,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"576": {
|
613 |
+
"content": "<|gu|>",
|
614 |
+
"lstrip": true,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": true,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"577": {
|
621 |
+
"content": "<|am|>",
|
622 |
+
"lstrip": true,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": true,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"578": {
|
629 |
+
"content": "<|yi|>",
|
630 |
+
"lstrip": true,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": true,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"579": {
|
637 |
+
"content": "<|lo|>",
|
638 |
+
"lstrip": true,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": true,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"580": {
|
645 |
+
"content": "<|uz|>",
|
646 |
+
"lstrip": true,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": true,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"581": {
|
653 |
+
"content": "<|fo|>",
|
654 |
+
"lstrip": true,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": true,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"582": {
|
661 |
+
"content": "<|ht|>",
|
662 |
+
"lstrip": true,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": true,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"583": {
|
669 |
+
"content": "<|ps|>",
|
670 |
+
"lstrip": true,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": true,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"584": {
|
677 |
+
"content": "<|tk|>",
|
678 |
+
"lstrip": true,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": true,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"585": {
|
685 |
+
"content": "<|nn|>",
|
686 |
+
"lstrip": true,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": true,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"586": {
|
693 |
+
"content": "<|mt|>",
|
694 |
+
"lstrip": true,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": true,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"587": {
|
701 |
+
"content": "<|sa|>",
|
702 |
+
"lstrip": true,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": true,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"588": {
|
709 |
+
"content": "<|lb|>",
|
710 |
+
"lstrip": true,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": true,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"589": {
|
717 |
+
"content": "<|my|>",
|
718 |
+
"lstrip": true,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": true,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"590": {
|
725 |
+
"content": "<|bo|>",
|
726 |
+
"lstrip": true,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": true,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"591": {
|
733 |
+
"content": "<|tl|>",
|
734 |
+
"lstrip": true,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": true,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"592": {
|
741 |
+
"content": "<|mg|>",
|
742 |
+
"lstrip": true,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": true,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"593": {
|
749 |
+
"content": "<|as|>",
|
750 |
+
"lstrip": true,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": true,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"594": {
|
757 |
+
"content": "<|tt|>",
|
758 |
+
"lstrip": true,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": true,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"595": {
|
765 |
+
"content": "<|haw|>",
|
766 |
+
"lstrip": true,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": true,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
},
|
772 |
+
"596": {
|
773 |
+
"content": "<|ln|>",
|
774 |
+
"lstrip": true,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": true,
|
777 |
+
"single_word": false,
|
778 |
+
"special": true
|
779 |
+
},
|
780 |
+
"597": {
|
781 |
+
"content": "<|ha|>",
|
782 |
+
"lstrip": true,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": true,
|
785 |
+
"single_word": false,
|
786 |
+
"special": true
|
787 |
+
},
|
788 |
+
"598": {
|
789 |
+
"content": "<|ba|>",
|
790 |
+
"lstrip": true,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": true,
|
793 |
+
"single_word": false,
|
794 |
+
"special": true
|
795 |
+
},
|
796 |
+
"599": {
|
797 |
+
"content": "<|jw|>",
|
798 |
+
"lstrip": true,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": true,
|
801 |
+
"single_word": false,
|
802 |
+
"special": true
|
803 |
+
},
|
804 |
+
"600": {
|
805 |
+
"content": "<|su|>",
|
806 |
+
"lstrip": true,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": true,
|
809 |
+
"single_word": false,
|
810 |
+
"special": true
|
811 |
+
},
|
812 |
+
"601": {
|
813 |
+
"content": "<|translate|>",
|
814 |
+
"lstrip": true,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": true,
|
817 |
+
"single_word": false,
|
818 |
+
"special": true
|
819 |
+
},
|
820 |
+
"602": {
|
821 |
+
"content": "<|transcribe|>",
|
822 |
+
"lstrip": true,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": true,
|
825 |
+
"single_word": false,
|
826 |
+
"special": true
|
827 |
+
},
|
828 |
+
"603": {
|
829 |
+
"content": "<|startoflm|>",
|
830 |
+
"lstrip": true,
|
831 |
+
"normalized": false,
|
832 |
+
"rstrip": true,
|
833 |
+
"single_word": false,
|
834 |
+
"special": true
|
835 |
+
},
|
836 |
+
"604": {
|
837 |
+
"content": "<|startofprev|>",
|
838 |
+
"lstrip": true,
|
839 |
+
"normalized": false,
|
840 |
+
"rstrip": true,
|
841 |
+
"single_word": false,
|
842 |
+
"special": true
|
843 |
+
},
|
844 |
+
"605": {
|
845 |
+
"content": "<|nocaptions|>",
|
846 |
+
"lstrip": true,
|
847 |
+
"normalized": false,
|
848 |
+
"rstrip": true,
|
849 |
+
"single_word": false,
|
850 |
+
"special": true
|
851 |
+
},
|
852 |
+
"606": {
|
853 |
+
"content": "<|notimestamps|>",
|
854 |
+
"lstrip": true,
|
855 |
+
"normalized": false,
|
856 |
+
"rstrip": true,
|
857 |
+
"single_word": false,
|
858 |
+
"special": true
|
859 |
+
}
|
860 |
+
},
|
861 |
+
"additional_special_tokens": [
|
862 |
+
"<|endoftext|>",
|
863 |
+
"<|startoftranscript|>",
|
864 |
+
"<|en|>",
|
865 |
+
"<|zh|>",
|
866 |
+
"<|de|>",
|
867 |
+
"<|es|>",
|
868 |
+
"<|ru|>",
|
869 |
+
"<|ko|>",
|
870 |
+
"<|fr|>",
|
871 |
+
"<|ja|>",
|
872 |
+
"<|pt|>",
|
873 |
+
"<|tr|>",
|
874 |
+
"<|pl|>",
|
875 |
+
"<|ca|>",
|
876 |
+
"<|nl|>",
|
877 |
+
"<|ar|>",
|
878 |
+
"<|sv|>",
|
879 |
+
"<|it|>",
|
880 |
+
"<|id|>",
|
881 |
+
"<|hi|>",
|
882 |
+
"<|fi|>",
|
883 |
+
"<|vi|>",
|
884 |
+
"<|he|>",
|
885 |
+
"<|uk|>",
|
886 |
+
"<|el|>",
|
887 |
+
"<|ms|>",
|
888 |
+
"<|cs|>",
|
889 |
+
"<|ro|>",
|
890 |
+
"<|da|>",
|
891 |
+
"<|hu|>",
|
892 |
+
"<|ta|>",
|
893 |
+
"<|no|>",
|
894 |
+
"<|th|>",
|
895 |
+
"<|ur|>",
|
896 |
+
"<|hr|>",
|
897 |
+
"<|bg|>",
|
898 |
+
"<|lt|>",
|
899 |
+
"<|la|>",
|
900 |
+
"<|mi|>",
|
901 |
+
"<|ml|>",
|
902 |
+
"<|cy|>",
|
903 |
+
"<|sk|>",
|
904 |
+
"<|te|>",
|
905 |
+
"<|fa|>",
|
906 |
+
"<|lv|>",
|
907 |
+
"<|bn|>",
|
908 |
+
"<|sr|>",
|
909 |
+
"<|az|>",
|
910 |
+
"<|sl|>",
|
911 |
+
"<|kn|>",
|
912 |
+
"<|et|>",
|
913 |
+
"<|mk|>",
|
914 |
+
"<|br|>",
|
915 |
+
"<|eu|>",
|
916 |
+
"<|is|>",
|
917 |
+
"<|hy|>",
|
918 |
+
"<|ne|>",
|
919 |
+
"<|mn|>",
|
920 |
+
"<|bs|>",
|
921 |
+
"<|kk|>",
|
922 |
+
"<|sq|>",
|
923 |
+
"<|sw|>",
|
924 |
+
"<|gl|>",
|
925 |
+
"<|mr|>",
|
926 |
+
"<|pa|>",
|
927 |
+
"<|si|>",
|
928 |
+
"<|km|>",
|
929 |
+
"<|sn|>",
|
930 |
+
"<|yo|>",
|
931 |
+
"<|so|>",
|
932 |
+
"<|af|>",
|
933 |
+
"<|oc|>",
|
934 |
+
"<|ka|>",
|
935 |
+
"<|be|>",
|
936 |
+
"<|tg|>",
|
937 |
+
"<|sd|>",
|
938 |
+
"<|gu|>",
|
939 |
+
"<|am|>",
|
940 |
+
"<|yi|>",
|
941 |
+
"<|lo|>",
|
942 |
+
"<|uz|>",
|
943 |
+
"<|fo|>",
|
944 |
+
"<|ht|>",
|
945 |
+
"<|ps|>",
|
946 |
+
"<|tk|>",
|
947 |
+
"<|nn|>",
|
948 |
+
"<|mt|>",
|
949 |
+
"<|sa|>",
|
950 |
+
"<|lb|>",
|
951 |
+
"<|my|>",
|
952 |
+
"<|bo|>",
|
953 |
+
"<|tl|>",
|
954 |
+
"<|mg|>",
|
955 |
+
"<|as|>",
|
956 |
+
"<|tt|>",
|
957 |
+
"<|haw|>",
|
958 |
+
"<|ln|>",
|
959 |
+
"<|ha|>",
|
960 |
+
"<|ba|>",
|
961 |
+
"<|jw|>",
|
962 |
+
"<|su|>",
|
963 |
+
"<|translate|>",
|
964 |
+
"<|transcribe|>",
|
965 |
+
"<|startoflm|>",
|
966 |
+
"<|startofprev|>",
|
967 |
+
"<|nocaptions|>",
|
968 |
+
"<|notimestamps|>"
|
969 |
+
],
|
970 |
+
"bos_token": "<|endoftext|>",
|
971 |
+
"clean_up_tokenization_spaces": true,
|
972 |
+
"eos_token": "<|endoftext|>",
|
973 |
+
"errors": "replace",
|
974 |
+
"model_max_length": 1000000000000000019884624838656,
|
975 |
+
"pad_token": "<|endoftext|>",
|
976 |
+
"tokenizer_class": "WhisperTokenizer",
|
977 |
+
"unk_token": "<|endoftext|>"
|
978 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,502 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"0": 0,
|
3 |
+
"1": 1,
|
4 |
+
"11": 57,
|
5 |
+
"13": 76,
|
6 |
+
"2": 2,
|
7 |
+
"21": 63,
|
8 |
+
"23": 168,
|
9 |
+
"24": 62,
|
10 |
+
"3": 3,
|
11 |
+
"4": 4,
|
12 |
+
"41": 110,
|
13 |
+
"42": 60,
|
14 |
+
"44": 123,
|
15 |
+
"442": 112,
|
16 |
+
"453": 58,
|
17 |
+
"5": 5,
|
18 |
+
"53": 56,
|
19 |
+
"533": 59,
|
20 |
+
"544": 124,
|
21 |
+
"55": 92,
|
22 |
+
"a": 6,
|
23 |
+
"ai": 69,
|
24 |
+
"akieu": 449,
|
25 |
+
"am": 447,
|
26 |
+
"an": 448,
|
27 |
+
"au": 77,
|
28 |
+
"aÅĭ": 93,
|
29 |
+
"aÊĶ": 200,
|
30 |
+
"b": 7,
|
31 |
+
"e": 8,
|
32 |
+
"eÅĭ": 118,
|
33 |
+
"eÊĶ": 116,
|
34 |
+
"h": 9,
|
35 |
+
"ha": 311,
|
36 |
+
"hai": 191,
|
37 |
+
"he": 176,
|
38 |
+
"hi": 204,
|
39 |
+
"hia": 406,
|
40 |
+
"ho": 252,
|
41 |
+
"hou": 278,
|
42 |
+
"hu": 73,
|
43 |
+
"hua": 105,
|
44 |
+
"huai": 129,
|
45 |
+
"hue": 132,
|
46 |
+
"hui": 147,
|
47 |
+
"huoi": 134,
|
48 |
+
"huɤɯ": 133,
|
49 |
+
"hy": 142,
|
50 |
+
"hya": 439,
|
51 |
+
"hyÉĴ": 405,
|
52 |
+
"hyÉĶ": 440,
|
53 |
+
"hÉĴ": 226,
|
54 |
+
"hÉĶ": 265,
|
55 |
+
"hÉĶu": 135,
|
56 |
+
"i": 10,
|
57 |
+
"ia": 83,
|
58 |
+
"iau": 136,
|
59 |
+
"ie": 95,
|
60 |
+
"ieu": 102,
|
61 |
+
"ieÅĭ": 238,
|
62 |
+
"ieÊĶ": 433,
|
63 |
+
"in": 163,
|
64 |
+
"iu": 97,
|
65 |
+
"iũ": 407,
|
66 |
+
"iÅĭ": 84,
|
67 |
+
"iÊĶ": 119,
|
68 |
+
"k": 11,
|
69 |
+
"kai": 192,
|
70 |
+
"kaÊĶ": 313,
|
71 |
+
"ke": 107,
|
72 |
+
"kh": 87,
|
73 |
+
"kha": 484,
|
74 |
+
"khe": 152,
|
75 |
+
"khi": 249,
|
76 |
+
"khieu": 427,
|
77 |
+
"khou": 392,
|
78 |
+
"khue": 451,
|
79 |
+
"khui": 312,
|
80 |
+
"khuɤɯ": 452,
|
81 |
+
"khy": 237,
|
82 |
+
"khÉĴ": 223,
|
83 |
+
"khÉĶ": 303,
|
84 |
+
"khÉĶu": 175,
|
85 |
+
"ki": 205,
|
86 |
+
"kiau": 409,
|
87 |
+
"kieu": 229,
|
88 |
+
"kin": 363,
|
89 |
+
"kiÅĭ": 343,
|
90 |
+
"kiÉĽu": 443,
|
91 |
+
"ko": 239,
|
92 |
+
"kou": 450,
|
93 |
+
"ku": 108,
|
94 |
+
"kua": 143,
|
95 |
+
"kuai": 335,
|
96 |
+
"kue": 305,
|
97 |
+
"kuoi": 307,
|
98 |
+
"kuɤɯ": 306,
|
99 |
+
"ky": 130,
|
100 |
+
"kø": 362,
|
101 |
+
"kɤɯ": 408,
|
102 |
+
"kÉĴ": 177,
|
103 |
+
"kÉĶ": 227,
|
104 |
+
"kÉĶu": 228,
|
105 |
+
"l": 12,
|
106 |
+
"le": 240,
|
107 |
+
"li": 145,
|
108 |
+
"liu": 456,
|
109 |
+
"liÊĶ": 365,
|
110 |
+
"lo": 253,
|
111 |
+
"lou": 457,
|
112 |
+
"lua": 454,
|
113 |
+
"lui": 254,
|
114 |
+
"ly": 293,
|
115 |
+
"lø": 410,
|
116 |
+
"lɤɯ": 455,
|
117 |
+
"lÉĴ": 364,
|
118 |
+
"lÉĶ": 453,
|
119 |
+
"lÉĶu": 241,
|
120 |
+
"m": 13,
|
121 |
+
"ma": 215,
|
122 |
+
"min": 460,
|
123 |
+
"miÅĭ": 314,
|
124 |
+
"mui": 459,
|
125 |
+
"mÉĴ": 366,
|
126 |
+
"mÉĶ": 458,
|
127 |
+
"n": 14,
|
128 |
+
"ni": 279,
|
129 |
+
"niÅĭ": 461,
|
130 |
+
"nÉĶu": 367,
|
131 |
+
"o": 15,
|
132 |
+
"oi": 100,
|
133 |
+
"on": 462,
|
134 |
+
"ou": 98,
|
135 |
+
"oÅĭ": 180,
|
136 |
+
"p": 16,
|
137 |
+
"pa": 255,
|
138 |
+
"pai": 131,
|
139 |
+
"pau": 463,
|
140 |
+
"pe": 120,
|
141 |
+
"peÊĶ": 465,
|
142 |
+
"ph": 113,
|
143 |
+
"phai": 336,
|
144 |
+
"phaÅĭ": 337,
|
145 |
+
"phou": 403,
|
146 |
+
"phua": 315,
|
147 |
+
"phuai": 369,
|
148 |
+
"phue": 370,
|
149 |
+
"phuoi": 372,
|
150 |
+
"phuɤɯ": 371,
|
151 |
+
"phÉĶu": 199,
|
152 |
+
"pi": 201,
|
153 |
+
"piÅĭ": 242,
|
154 |
+
"po": 256,
|
155 |
+
"pou": 368,
|
156 |
+
"pu": 91,
|
157 |
+
"pua": 266,
|
158 |
+
"puai": 197,
|
159 |
+
"pue": 189,
|
160 |
+
"puoi": 198,
|
161 |
+
"puɤɯ": 190,
|
162 |
+
"pɤɯ": 411,
|
163 |
+
"pÉĴ": 206,
|
164 |
+
"pÉĶ": 257,
|
165 |
+
"pÉĶu": 193,
|
166 |
+
"pÉĽ": 464,
|
167 |
+
"s": 17,
|
168 |
+
"t": 18,
|
169 |
+
"ta": 280,
|
170 |
+
"tai": 317,
|
171 |
+
"te": 153,
|
172 |
+
"teÅĭ": 467,
|
173 |
+
"th": 103,
|
174 |
+
"thai": 292,
|
175 |
+
"thau": 498,
|
176 |
+
"thaÅĭ": 499,
|
177 |
+
"thi": 291,
|
178 |
+
"thiu": 334,
|
179 |
+
"thiÅĭ": 402,
|
180 |
+
"thua": 267,
|
181 |
+
"thui": 319,
|
182 |
+
"thy": 401,
|
183 |
+
"thÉĶu": 276,
|
184 |
+
"ti": 169,
|
185 |
+
"tiu": 345,
|
186 |
+
"tiÅĭ": 466,
|
187 |
+
"to": 316,
|
188 |
+
"tou": 294,
|
189 |
+
"ts": 66,
|
190 |
+
"tsai": 322,
|
191 |
+
"tse": 270,
|
192 |
+
"tsh": 81,
|
193 |
+
"tsha": 353,
|
194 |
+
"tshai": 236,
|
195 |
+
"tshau": 425,
|
196 |
+
"tshaÅĭ": 483,
|
197 |
+
"tsheÅĭ": 426,
|
198 |
+
"tshi": 235,
|
199 |
+
"tshia": 301,
|
200 |
+
"tshiu": 261,
|
201 |
+
"tshui": 323,
|
202 |
+
"tshy": 213,
|
203 |
+
"tshø": 331,
|
204 |
+
"tshÉĴ": 390,
|
205 |
+
"tshÉĴÊĶ": 391,
|
206 |
+
"tshÉĶ": 389,
|
207 |
+
"tsi": 271,
|
208 |
+
"tsia": 194,
|
209 |
+
"tsiau": 472,
|
210 |
+
"tsieu": 297,
|
211 |
+
"tso": 230,
|
212 |
+
"tsou": 471,
|
213 |
+
"tsui": 210,
|
214 |
+
"tsy": 203,
|
215 |
+
"tsɤɯ": 416,
|
216 |
+
"tsÉĴ": 470,
|
217 |
+
"tsÉĶ": 469,
|
218 |
+
"tsÉĶu": 259,
|
219 |
+
"tua": 140,
|
220 |
+
"tui": 318,
|
221 |
+
"ty": 139,
|
222 |
+
"tø": 295,
|
223 |
+
"tÉĴ": 344,
|
224 |
+
"tÉĶ": 373,
|
225 |
+
"tÉĶu": 144,
|
226 |
+
"u": 19,
|
227 |
+
"ua": 78,
|
228 |
+
"uai": 202,
|
229 |
+
"ue": 216,
|
230 |
+
"ui": 94,
|
231 |
+
"uoi": 269,
|
232 |
+
"uɤɯ": 268,
|
233 |
+
"y": 20,
|
234 |
+
"£": 21,
|
235 |
+
"¤": 22,
|
236 |
+
"¦": 23,
|
237 |
+
"©": 24,
|
238 |
+
"¬": 25,
|
239 |
+
"¯": 26,
|
240 |
+
"²": 27,
|
241 |
+
"¸": 28,
|
242 |
+
"¼": 29,
|
243 |
+
"¾": 30,
|
244 |
+
"Ã": 31,
|
245 |
+
"ã": 141,
|
246 |
+
"ø": 101,
|
247 |
+
"øn": 496,
|
248 |
+
"øÅĭ": 434,
|
249 |
+
"øÊĶ": 497,
|
250 |
+
"Ä": 32,
|
251 |
+
"Ä©": 243,
|
252 |
+
"Å": 33,
|
253 |
+
"Å©": 281,
|
254 |
+
"Åĭ": 65,
|
255 |
+
"ÅĭÉĶu": 296,
|
256 |
+
"Åĵ": 374,
|
257 |
+
"Ç": 34,
|
258 |
+
"Ǿ": 61,
|
259 |
+
"Ǿai": 320,
|
260 |
+
"Ǿau": 245,
|
261 |
+
"ǾaÅĭ": 258,
|
262 |
+
"Ǿe": 146,
|
263 |
+
"Ǿi": 244,
|
264 |
+
"Ǿia": 156,
|
265 |
+
"Ǿiu": 246,
|
266 |
+
"ǾiÅĭ": 415,
|
267 |
+
"Ǿo": 413,
|
268 |
+
"Ǿou": 321,
|
269 |
+
"Ǿu": 414,
|
270 |
+
"Ǿua": 209,
|
271 |
+
"Ǿy": 376,
|
272 |
+
"ǾÉĴ": 220,
|
273 |
+
"ǾÉĶ": 219,
|
274 |
+
"ǾÉĶu": 170,
|
275 |
+
"É": 35,
|
276 |
+
"ɤ": 82,
|
277 |
+
"ɤÅĭ": 222,
|
278 |
+
"ɤɯ": 86,
|
279 |
+
"ɤÊĶ": 302,
|
280 |
+
"ɬ": 67,
|
281 |
+
"ɬai": 298,
|
282 |
+
"ɬaÅĭ": 346,
|
283 |
+
"ɬe": 181,
|
284 |
+
"ɬi": 182,
|
285 |
+
"ɬia": 125,
|
286 |
+
"ɬiau": 324,
|
287 |
+
"ɬieu": 282,
|
288 |
+
"ɬiu": 417,
|
289 |
+
"ɬiÊĶ": 473,
|
290 |
+
"ɬo": 221,
|
291 |
+
"ɬu": 247,
|
292 |
+
"ɬua": 184,
|
293 |
+
"ɬy": 183,
|
294 |
+
"ɬø": 185,
|
295 |
+
"ɬÉĶu": 377,
|
296 |
+
"ɬÉĶÊĶ": 418,
|
297 |
+
"ɯ": 85,
|
298 |
+
"ÉĴ": 74,
|
299 |
+
"ÉĴÊĶ": 186,
|
300 |
+
"ÉĶ": 64,
|
301 |
+
"ÉĶu": 72,
|
302 |
+
"ÉĶÅĭ": 117,
|
303 |
+
"ÉĶÊĶ": 122,
|
304 |
+
"ÉĽ": 99,
|
305 |
+
"ÉĽn": 400,
|
306 |
+
"ÉĽu": 173,
|
307 |
+
"ÉĽÅĭ": 264,
|
308 |
+
"Ê": 36,
|
309 |
+
"ÊĶ": 75,
|
310 |
+
"Ì": 37,
|
311 |
+
"Ìĥ": 106,
|
312 |
+
"Î": 38,
|
313 |
+
"β": 217,
|
314 |
+
"ã": 39,
|
315 |
+
"ãĢ": 158,
|
316 |
+
"ï": 40,
|
317 |
+
"ï¼": 207,
|
318 |
+
"Ċ": 41,
|
319 |
+
"č": 42,
|
320 |
+
"čĊ": 54,
|
321 |
+
"Ġ": 43,
|
322 |
+
"Ġh": 109,
|
323 |
+
"Ġha": 250,
|
324 |
+
"ĠhiÅ©": 435,
|
325 |
+
"Ġhu": 412,
|
326 |
+
"Ġhua": 468,
|
327 |
+
"ĠhÉĴ": 251,
|
328 |
+
"ĠhÉĶ": 308,
|
329 |
+
"Ġk": 71,
|
330 |
+
"Ġka": 178,
|
331 |
+
"Ġkai": 161,
|
332 |
+
"Ġkau": 274,
|
333 |
+
"ĠkaÅĭ": 382,
|
334 |
+
"ĠkeÊĶ": 328,
|
335 |
+
"Ġkh": 121,
|
336 |
+
"Ġkhai": 309,
|
337 |
+
"Ġkhi": 339,
|
338 |
+
"Ġkhu": 381,
|
339 |
+
"Ġkhua": 476,
|
340 |
+
"Ġki": 327,
|
341 |
+
"Ġkia": 421,
|
342 |
+
"ĠkiÅĭ": 475,
|
343 |
+
"Ġko": 273,
|
344 |
+
"ĠkoÊĶ": 446,
|
345 |
+
"Ġku": 155,
|
346 |
+
"Ġkua": 212,
|
347 |
+
"Ġkuai": 441,
|
348 |
+
"Ġkuɤɯ": 360,
|
349 |
+
"Ġky": 284,
|
350 |
+
"ĠkÉĴ": 172,
|
351 |
+
"ĠkÉĶ": 166,
|
352 |
+
"ĠkÉĶu": 285,
|
353 |
+
"ĠkÉĶÅĭ": 383,
|
354 |
+
"Ġl": 70,
|
355 |
+
"Ġlai": 171,
|
356 |
+
"Ġlau": 111,
|
357 |
+
"ĠlaÅĭ": 299,
|
358 |
+
"Ġle": 164,
|
359 |
+
"ĠleÅĭ": 420,
|
360 |
+
"ĠleÊĶ": 233,
|
361 |
+
"Ġli": 104,
|
362 |
+
"Ġlia": 380,
|
363 |
+
"Ġliu": 300,
|
364 |
+
"ĠliÊĶ": 225,
|
365 |
+
"Ġlo": 326,
|
366 |
+
"Ġlua": 474,
|
367 |
+
"Ġlui": 165,
|
368 |
+
"Ġly": 349,
|
369 |
+
"ĠlÉĴ": 379,
|
370 |
+
"ĠlÉĽ": 195,
|
371 |
+
"ĠlÉĽÊĶ": 361,
|
372 |
+
"Ġm": 88,
|
373 |
+
"Ġma": 126,
|
374 |
+
"Ġmai": 262,
|
375 |
+
"Ġme": 485,
|
376 |
+
"Ġmi": 275,
|
377 |
+
"Ġmia": 429,
|
378 |
+
"ĠmiÅĭ": 393,
|
379 |
+
"Ġmua": 289,
|
380 |
+
"Ġmuai": 430,
|
381 |
+
"Ġmue": 486,
|
382 |
+
"ĠmÉĴ": 332,
|
383 |
+
"ĠmÉĶ": 428,
|
384 |
+
"Ġn": 79,
|
385 |
+
"Ġnai": 329,
|
386 |
+
"Ġnau": 157,
|
387 |
+
"ĠnaÅĭ": 385,
|
388 |
+
"Ġne": 350,
|
389 |
+
"Ġni": 150,
|
390 |
+
"Ġnieu": 387,
|
391 |
+
"ĠniÅĭ": 128,
|
392 |
+
"Ġnu": 351,
|
393 |
+
"Ġnua": 478,
|
394 |
+
"Ġnui": 286,
|
395 |
+
"Ġny": 422,
|
396 |
+
"Ġnø": 386,
|
397 |
+
"ĠnÉĴ": 384,
|
398 |
+
"ĠnÉĶ": 477,
|
399 |
+
"ĠnÉĶÅĭ": 479,
|
400 |
+
"Ġp": 96,
|
401 |
+
"Ġpai": 304,
|
402 |
+
"Ġph": 148,
|
403 |
+
"Ġphi": 342,
|
404 |
+
"ĠpiÊĶ": 495,
|
405 |
+
"Ġpo": 224,
|
406 |
+
"Ġpu": 375,
|
407 |
+
"Ġpɤɯ": 356,
|
408 |
+
"ĠpÉĶÊĶ": 399,
|
409 |
+
"Ġt": 89,
|
410 |
+
"Ġtai": 214,
|
411 |
+
"Ġtau": 396,
|
412 |
+
"Ġte": 196,
|
413 |
+
"ĠteÅĭ": 290,
|
414 |
+
"Ġth": 487,
|
415 |
+
"Ġthe": 333,
|
416 |
+
"Ġti": 394,
|
417 |
+
"Ġts": 90,
|
418 |
+
"Ġtse": 354,
|
419 |
+
"ĠtseÊĶ": 398,
|
420 |
+
"Ġtsh": 137,
|
421 |
+
"Ġtshy": 341,
|
422 |
+
"Ġtsi": 188,
|
423 |
+
"Ġtsia": 263,
|
424 |
+
"Ġtsieu": 432,
|
425 |
+
"ĠtsiÅĭ": 492,
|
426 |
+
"ĠtsiÊĶ": 493,
|
427 |
+
"Ġtsui": 355,
|
428 |
+
"Ġtsy": 179,
|
429 |
+
"ĠtsÉĴ": 491,
|
430 |
+
"ĠtsÉĴÊĶ": 494,
|
431 |
+
"ĠtsÉĶ": 397,
|
432 |
+
"Ġtua": 489,
|
433 |
+
"Ġtui": 490,
|
434 |
+
"Ġty": 431,
|
435 |
+
"ĠtÉĴ": 395,
|
436 |
+
"ĠtÉĶ": 488,
|
437 |
+
"ĠÅĭ": 127,
|
438 |
+
"ĠÅĭiÅĭ": 359,
|
439 |
+
"ĠÅĭua": 340,
|
440 |
+
"ĠÅĭÉĶu": 404,
|
441 |
+
"ĠǾ": 68,
|
442 |
+
"ĠǾa": 160,
|
443 |
+
"ĠǾau": 138,
|
444 |
+
"ĠǾaÅĭ": 211,
|
445 |
+
"ĠǾe": 260,
|
446 |
+
"ĠǾeÊĶ": 419,
|
447 |
+
"ĠǾi": 114,
|
448 |
+
"ĠǾia": 325,
|
449 |
+
"ĠǾiau": 437,
|
450 |
+
"ĠǾiu": 231,
|
451 |
+
"ĠǾiÅĭ": 272,
|
452 |
+
"ĠǾiÊĶ": 436,
|
453 |
+
"ĠǾo": 378,
|
454 |
+
"ĠǾou": 348,
|
455 |
+
"ĠǾu": 115,
|
456 |
+
"ĠǾua": 149,
|
457 |
+
"ĠǾuai": 338,
|
458 |
+
"ĠǾue": 357,
|
459 |
+
"ĠǾuoi": 358,
|
460 |
+
"ĠǾuã": 438,
|
461 |
+
"ĠǾy": 174,
|
462 |
+
"ĠǾyÅĭ": 442,
|
463 |
+
"ĠǾÉĴ": 154,
|
464 |
+
"ĠǾÉĴÅĭ": 310,
|
465 |
+
"ĠǾÉĶ": 347,
|
466 |
+
"ĠǾÉĶu": 248,
|
467 |
+
"ĠǾÉĶÅĭ": 283,
|
468 |
+
"ĠÇ¾ÉĽ": 232,
|
469 |
+
"ĠÇ¾ÉĽÊĶ": 445,
|
470 |
+
"Ġɬ": 80,
|
471 |
+
"Ġɬa": 330,
|
472 |
+
"Ġɬe": 151,
|
473 |
+
"Ġɬi": 187,
|
474 |
+
"Ġɬia": 234,
|
475 |
+
"Ġɬieu": 352,
|
476 |
+
"ĠɬiÊĶ": 288,
|
477 |
+
"Ġɬo": 480,
|
478 |
+
"Ġɬu": 423,
|
479 |
+
"Ġɬui": 481,
|
480 |
+
"Ġɬy": 167,
|
481 |
+
"ĠɬÉĴ": 424,
|
482 |
+
"ĠɬÉĶ": 388,
|
483 |
+
"ĠɬÉĶu": 287,
|
484 |
+
"ĠɬÉĶÊĶ": 482,
|
485 |
+
"Ġβ": 218,
|
486 |
+
"ĠãĢ": 159,
|
487 |
+
"ĠãĢĤ": 162,
|
488 |
+
"Ġï¼": 208,
|
489 |
+
"Ġï¼Į": 444,
|
490 |
+
"Ġï¼Ł": 277,
|
491 |
+
"ĠčĊ": 55,
|
492 |
+
"Ģ": 44,
|
493 |
+
"Ĥ": 45,
|
494 |
+
"ĥ": 46,
|
495 |
+
"ĭ": 47,
|
496 |
+
"Į": 48,
|
497 |
+
"Ĵ": 49,
|
498 |
+
"ĵ": 50,
|
499 |
+
"Ķ": 51,
|
500 |
+
"Ľ": 52,
|
501 |
+
"Ł": 53
|
502 |
+
}
|