nguyenvulebinh commited on
Commit
298d5a7
·
verified ·
1 Parent(s): e6efdd5

Upload tokenizer

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86684c9285ff3483ec4dcd52d9a56b1fb5184d9473774d59c305597c98e3b04b
3
+ size 250003
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "additional_special_tokens": [],
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": true,
39
+ "do_lower_case": false,
40
+ "do_upper_case": false,
41
+ "eos_token": "</s>",
42
+ "lang_codes": null,
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "pad_token": "<pad>",
45
+ "sp_model_kwargs": {},
46
+ "tgt_lang": null,
47
+ "tokenizer_class": "Speech2TextTokenizer",
48
+ "unk_token": "<unk>"
49
+ }
vocab.json ADDED
@@ -0,0 +1,1002 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<s>": 0,
3
+ "<pad>": 1,
4
+ "</s>": 2,
5
+ "<unk>": 3,
6
+ "<ar>": 4,
7
+ "<de>": 5,
8
+ "<el>": 6,
9
+ "<es>": 7,
10
+ "<fr>": 8,
11
+ "<it>": 9,
12
+ "<pt>": 10,
13
+ "<ru>": 11,
14
+ "\u2581": 12,
15
+ "s": 13,
16
+ ",": 14,
17
+ "a": 15,
18
+ "\u2581a": 16,
19
+ "\u2581\"": 17,
20
+ "\u2581de": 18,
21
+ "r": 19,
22
+ "i": 20,
23
+ ".\"": 21,
24
+ "e": 22,
25
+ "n": 23,
26
+ "u": 24,
27
+ "o": 25,
28
+ "\u2581que": 26,
29
+ "re": 27,
30
+ "'": 28,
31
+ "m": 29,
32
+ "c": 30,
33
+ ".": 31,
34
+ "l": 32,
35
+ "t": 33,
36
+ "ra": 34,
37
+ "\u2581la": 35,
38
+ "\u00e9": 36,
39
+ "p": 37,
40
+ "te": 38,
41
+ "to": 39,
42
+ "ta": 40,
43
+ "er": 41,
44
+ "\u2581di": 42,
45
+ "ca": 43,
46
+ "f": 44,
47
+ "\u2581en": 45,
48
+ "g": 46,
49
+ "\u2581un": 47,
50
+ "co": 48,
51
+ "\u2581se": 49,
52
+ "\u2581con": 50,
53
+ "da": 51,
54
+ "ci": 52,
55
+ "de": 53,
56
+ "le": 54,
57
+ "ti": 55,
58
+ "ce": 56,
59
+ "la": 57,
60
+ "d": 58,
61
+ "ma": 59,
62
+ "ro": 60,
63
+ "\u0435": 61,
64
+ "is": 62,
65
+ "li": 63,
66
+ "do": 64,
67
+ "en": 65,
68
+ "\u2581me": 66,
69
+ "pe": 67,
70
+ "\u2581e": 68,
71
+ "no": 69,
72
+ "es": 70,
73
+ "ar": 71,
74
+ "\u0441": 72,
75
+ "\u2581o": 73,
76
+ "ve": 74,
77
+ "\u2581es": 75,
78
+ "ne": 76,
79
+ "mo": 77,
80
+ "z": 78,
81
+ "va": 79,
82
+ "na": 80,
83
+ "di": 81,
84
+ "\u2581y": 82,
85
+ "\u2581no": 83,
86
+ "\u0443": 84,
87
+ "ri": 85,
88
+ "in": 86,
89
+ "lo": 87,
90
+ "b": 88,
91
+ "mos": 89,
92
+ "\u2581le": 90,
93
+ "vo": 91,
94
+ "\u2581in": 92,
95
+ "\u2581po": 93,
96
+ "me": 94,
97
+ "\u03bd": 95,
98
+ "\u2581ma": 96,
99
+ "\u00ed": 97,
100
+ "ni": 98,
101
+ "on": 99,
102
+ "\u00e1": 100,
103
+ "\u2581c": 101,
104
+ "y": 102,
105
+ "-": 103,
106
+ "que": 104,
107
+ "h": 105,
108
+ "\u03c3": 106,
109
+ "\u0627": 107,
110
+ "\u2581fa": 108,
111
+ "mi": 109,
112
+ "\u043c": 110,
113
+ "est": 111,
114
+ "vi": 112,
115
+ "se": 113,
116
+ "\u2581el": 114,
117
+ "ba": 115,
118
+ "as": 116,
119
+ "\u0438": 117,
120
+ "\u043e": 118,
121
+ "an": 119,
122
+ "gu": 120,
123
+ "ment": 121,
124
+ "al": 122,
125
+ "\u03b1": 123,
126
+ "\u03b9": 124,
127
+ ":": 125,
128
+ "\u2581\u00e0": 126,
129
+ "\u00f3": 127,
130
+ "\u03b5": 128,
131
+ "\u03bf": 129,
132
+ "\u064a": 130,
133
+ "ur": 131,
134
+ "v": 132,
135
+ "\u2581per": 133,
136
+ "\u044f": 134,
137
+ "\u2581pro": 135,
138
+ "\u2581des": 136,
139
+ "si": 137,
140
+ "po": 138,
141
+ "\u2581si": 139,
142
+ "\u03bb": 140,
143
+ "\u2581\u00e9": 141,
144
+ "\u2581che": 142,
145
+ "\u2581et": 143,
146
+ "\"\"": 144,
147
+ "it": 145,
148
+ "os": 146,
149
+ "\u2581mi": 147,
150
+ "\u03c1": 148,
151
+ "\u03c2": 149,
152
+ "\u2581d": 150,
153
+ "\u043d": 151,
154
+ "\u2581l": 152,
155
+ "\u2581pas": 153,
156
+ "\u2581su": 154,
157
+ "\u0430": 155,
158
+ "\u2581do": 156,
159
+ "res": 157,
160
+ "tro": 158,
161
+ "go": 159,
162
+ "\u03ac": 160,
163
+ "\u2581qui": 161,
164
+ "\u0644": 162,
165
+ "\u0645": 163,
166
+ "so": 164,
167
+ "nd": 165,
168
+ "E": 166,
169
+ "\u0440": 167,
170
+ "\u2581qu": 168,
171
+ "ge": 169,
172
+ "lle": 170,
173
+ "sta": 171,
174
+ "\u2581una": 172,
175
+ "\u0442": 173,
176
+ "\u044b": 174,
177
+ "or": 175,
178
+ "tra": 176,
179
+ "\u2581par": 177,
180
+ "ir": 178,
181
+ "\u2581al": 179,
182
+ "\u2581les": 180,
183
+ "\u0437": 181,
184
+ "\u2581da": 182,
185
+ "t\u00e9": 183,
186
+ "A": 184,
187
+ "mente": 185,
188
+ "\u0432": 186,
189
+ "gi": 187,
190
+ "\u0646": 188,
191
+ "tu": 189,
192
+ "\u2581il": 190,
193
+ "\u2581so": 191,
194
+ "\u2581ne": 192,
195
+ "\u0648": 193,
196
+ "ch": 194,
197
+ "\u043d\u043e": 195,
198
+ "\u0442\u043e": 196,
199
+ "\u2581vi": 197,
200
+ "\u062a": 198,
201
+ "ga": 199,
202
+ "\u2581eu": 200,
203
+ "fi": 201,
204
+ "\u2581com": 202,
205
+ "pa": 203,
206
+ "\u0434": 204,
207
+ "\u2581ha": 205,
208
+ "M": 206,
209
+ "lu": 207,
210
+ "\u03c4": 208,
211
+ "\u0439": 209,
212
+ "?": 210,
213
+ "\u043b": 211,
214
+ "\u2581lo": 212,
215
+ "\u03bc": 213,
216
+ "\u2581je": 214,
217
+ "bi": 215,
218
+ "\u2581para": 216,
219
+ "ter": 217,
220
+ "nt": 218,
221
+ "\u043f": 219,
222
+ "\u03ba": 220,
223
+ "\u03cc": 221,
224
+ "x": 222,
225
+ "ai": 223,
226
+ "\u03ad": 224,
227
+ "\u2581\u0441": 225,
228
+ "\u00e3o": 226,
229
+ "\u0631": 227,
230
+ "\u2581sa": 228,
231
+ "ndo": 229,
232
+ "\u2581por": 230,
233
+ "\u2581pa": 231,
234
+ "sso": 232,
235
+ "ten": 233,
236
+ "\u043a": 234,
237
+ "tre": 235,
238
+ "\u043d\u0438": 236,
239
+ "\u2581um": 237,
240
+ "\u0442\u044c": 238,
241
+ "\u2581los": 239,
242
+ "\u03af": 240,
243
+ "\u2581\u0627\u0644": 241,
244
+ "qui": 242,
245
+ "?\"": 243,
246
+ "un": 244,
247
+ "\u2581est": 245,
248
+ "\u2581vous": 246,
249
+ "lla": 247,
250
+ "\u2581j": 248,
251
+ "\u2581pour": 249,
252
+ "\u03b7": 250,
253
+ "\u0440\u0430": 251,
254
+ "us": 252,
255
+ "il": 253,
256
+ "tion": 254,
257
+ "\u2581ce": 255,
258
+ "\u00e8": 256,
259
+ "\u2581n\u00e3o": 257,
260
+ "\u2581uma": 258,
261
+ "du": 259,
262
+ "\u0445": 260,
263
+ "\u0639": 261,
264
+ "\u00eda": 262,
265
+ "\u043a\u043e": 263,
266
+ "C": 264,
267
+ "\u2581\"\"": 265,
268
+ "che": 266,
269
+ "\u0628": 267,
270
+ "\u2581une": 268,
271
+ "he": 269,
272
+ ")": 270,
273
+ "\u2581\u0432": 271,
274
+ "\u2581C": 272,
275
+ "O": 273,
276
+ "Y": 274,
277
+ "\u2581\u0438": 275,
278
+ "\u2581esta": 276,
279
+ "\u2581del": 277,
280
+ "ux": 278,
281
+ "ut": 279,
282
+ "ria": 280,
283
+ "k": 281,
284
+ "\u2581pre": 282,
285
+ "ent": 283,
286
+ "I": 284,
287
+ "\u0433": 285,
288
+ "za": 286,
289
+ "\u2581E": 287,
290
+ "\u0647": 288,
291
+ "\u2581dans": 289,
292
+ "gra": 290,
293
+ "ente": 291,
294
+ "\u2581\u043f\u043e": 292,
295
+ "\u2581gente": 293,
296
+ "\u2581pu": 294,
297
+ "cha": 295,
298
+ "\u043b\u0438": 296,
299
+ "\u2581mais": 297,
300
+ "\u2581na": 298,
301
+ "\u2581ou": 299,
302
+ "\u2581nos": 300,
303
+ "jo": 301,
304
+ "R": 302,
305
+ "\u03b3": 303,
306
+ "\u2581A": 304,
307
+ "\u03c9": 305,
308
+ "\u2581va": 306,
309
+ "\u2581como": 307,
310
+ "1": 308,
311
+ "\u0643": 309,
312
+ "\u03b4": 310,
313
+ "\u0441\u0442": 311,
314
+ "D": 312,
315
+ "pi": 313,
316
+ "\u2581comp": 314,
317
+ "\u2581em": 315,
318
+ "ble": 316,
319
+ "\u0433\u043e": 317,
320
+ "P": 318,
321
+ "\u2581pr": 319,
322
+ "\u2581mon": 320,
323
+ "\u2581tem": 321,
324
+ "\u062f": 322,
325
+ "\u2581du": 323,
326
+ "\u03c0": 324,
327
+ "\u0431": 325,
328
+ "\u2581\u043d\u0430": 326,
329
+ "\u2581pra": 327,
330
+ "\u03c7": 328,
331
+ "\u2581\u00e8": 329,
332
+ "\u0432\u043e": 330,
333
+ "ces": 331,
334
+ "\u0436": 332,
335
+ "\u0448": 333,
336
+ "\u2581au": 334,
337
+ "ci\u00f3n": 335,
338
+ "\u2581on": 336,
339
+ "ha": 337,
340
+ "\u2581d\u00e9": 338,
341
+ "sse": 339,
342
+ "0": 340,
343
+ "ste": 341,
344
+ "nos": 342,
345
+ "\u0623": 343,
346
+ "\u2581cu": 344,
347
+ "\u2581mu": 345,
348
+ "\u044e": 346,
349
+ "ver": 347,
350
+ "les": 348,
351
+ "\u00ea": 349,
352
+ "je": 350,
353
+ "N": 351,
354
+ "ando": 352,
355
+ "\u0432\u0430": 353,
356
+ "\u00fa": 354,
357
+ "\u03bf\u03c5": 355,
358
+ "\u2581ho": 356,
359
+ "mp": 357,
360
+ "pre": 358,
361
+ "w": 359,
362
+ "ho": 360,
363
+ "\u0442\u0435": 361,
364
+ "\u03c4\u03b1": 362,
365
+ "cia": 363,
366
+ "\u03ae": 364,
367
+ "sti": 365,
368
+ "\u03b5\u03b9": 366,
369
+ "\u2581\u00ab": 367,
370
+ "\u0629": 368,
371
+ "\u2581P": 369,
372
+ "nta": 370,
373
+ "\u2019": 371,
374
+ "cer": 372,
375
+ "F": 373,
376
+ "\u0434\u0435": 374,
377
+ "\u2581ser": 375,
378
+ "\u2581todo": 376,
379
+ "ja": 377,
380
+ "L": 378,
381
+ "zi": 379,
382
+ "\u2581tra": 380,
383
+ "\u2581S": 381,
384
+ "qu": 382,
385
+ "ado": 383,
386
+ "chi": 384,
387
+ "nde": 385,
388
+ "be": 386,
389
+ "\u00e7a": 387,
390
+ "\u03c5": 388,
391
+ "nu": 389,
392
+ "ue": 390,
393
+ "\u2581est\u00e1": 391,
394
+ "\u2581(": 392,
395
+ "\u03c4\u03b7": 393,
396
+ "dos": 394,
397
+ "\u043b\u044c": 395,
398
+ "rio": 396,
399
+ "\u2581non": 397,
400
+ "\u0633": 398,
401
+ "Et": 399,
402
+ "\u03bc\u03b5": 400,
403
+ "\u0440\u043e": 401,
404
+ "\u044c": 402,
405
+ "\u043d\u0430": 403,
406
+ "\u2581plus": 404,
407
+ "ssa": 405,
408
+ "forma": 406,
409
+ "bo": 407,
410
+ "\u2581tu": 408,
411
+ "ssi": 409,
412
+ "tar": 410,
413
+ "\u03b8": 411,
414
+ "ante": 412,
415
+ "nto": 413,
416
+ "\u2581las": 414,
417
+ "\u2581T": 415,
418
+ "\u2581sur": 416,
419
+ "gen": 417,
420
+ "nti": 418,
421
+ "gar": 419,
422
+ "ant": 420,
423
+ "\u043b\u0430": 421,
424
+ "V": 422,
425
+ "io": 423,
426
+ "No": 424,
427
+ "\u2581nous": 425,
428
+ "\u2581fo": 426,
429
+ "ven": 427,
430
+ "\u0434\u0430": 428,
431
+ "\u2581era": 429,
432
+ "cul": 430,
433
+ "ez": 431,
434
+ "\u2581\u043d\u0435": 432,
435
+ "\u2581\u03c0": 433,
436
+ "llo": 434,
437
+ "ul": 435,
438
+ "bu": 436,
439
+ "tto": 437,
440
+ "r\u00e9": 438,
441
+ "\u043a\u0430": 439,
442
+ "\u0435\u043d": 440,
443
+ "gli": 441,
444
+ "\u2581m\u00e1s": 442,
445
+ "\u2581ver": 443,
446
+ "ie": 444,
447
+ "idade": 445,
448
+ "\u2581porque": 446,
449
+ "\u2581\u00e7a": 447,
450
+ "La": 448,
451
+ "...": 449,
452
+ "\u2581\u0447\u0442\u043e": 450,
453
+ "\u03c0\u03bf": 451,
454
+ "tri": 452,
455
+ "iamo": 453,
456
+ "elle": 454,
457
+ "n\u00e9": 455,
458
+ "\u0642": 456,
459
+ "\u03bc\u03b1": 457,
460
+ "\u2581\u00bf": 458,
461
+ "G": 459,
462
+ "\u0641": 460,
463
+ "\u062d": 461,
464
+ "\u2581tout": 462,
465
+ "H": 463,
466
+ "idad": 464,
467
+ "\u043b\u043e": 465,
468
+ "\u2581voc\u00ea": 466,
469
+ "\u2581ex": 467,
470
+ "sion": 468,
471
+ "mento": 469,
472
+ "au": 470,
473
+ "\u2581r\u00e9": 471,
474
+ "\u2581pl": 472,
475
+ "J": 473,
476
+ "\u2581come": 474,
477
+ "\u043b\u0435": 475,
478
+ "ide": 476,
479
+ "ff": 477,
480
+ "\u0435\u0440": 478,
481
+ "\u00e8re": 479,
482
+ "T": 480,
483
+ "\u0435\u0442": 481,
484
+ "\u0451": 482,
485
+ "Je": 483,
486
+ "cio": 484,
487
+ "tte": 485,
488
+ "S": 486,
489
+ "cos": 487,
490
+ "\u2581bo": 488,
491
+ "5": 489,
492
+ "\u2581ve": 490,
493
+ "cre": 491,
494
+ "\u0441\u044f": 492,
495
+ "\u0442\u0438": 493,
496
+ "tant": 494,
497
+ "\u2581\u03bd\u03b1": 495,
498
+ "ol": 496,
499
+ "\u2581\u044d\u0442\u043e": 497,
500
+ "cri": 498,
501
+ "\u2581imp": 499,
502
+ "m\u00e9": 500,
503
+ "\u2581B": 501,
504
+ ";": 502,
505
+ "\u2581bien": 503,
506
+ "Es": 504,
507
+ "\u2581fait": 505,
508
+ "\u2581son": 506,
509
+ "\u03c4\u03b9": 507,
510
+ "ju": 508,
511
+ "\u03c6": 509,
512
+ "\u2581\u00bb": 510,
513
+ "\u2581car": 511,
514
+ "\u2581be": 512,
515
+ "Il": 513,
516
+ "\u2581avec": 514,
517
+ "\u0447": 515,
518
+ "ine": 516,
519
+ "\u03ce": 517,
520
+ "dia": 518,
521
+ "tura": 519,
522
+ "Eu": 520,
523
+ "ali": 521,
524
+ "\u2581comme": 522,
525
+ "2": 523,
526
+ "\u043e\u0442": 524,
527
+ "!": 525,
528
+ "\u00e7\u00e3o": 526,
529
+ "\u00e0": 527,
530
+ "Por": 528,
531
+ "\u0436\u0435": 529,
532
+ "\u2581muito": 530,
533
+ "ser": 531,
534
+ "t\u00e0": 532,
535
+ "\u2581for": 533,
536
+ "sent": 534,
537
+ "\u2581\u03c4\u03bf": 535,
538
+ "\u2581:": 536,
539
+ "cho": 537,
540
+ "\u03c4\u03b5": 538,
541
+ "Le": 539,
542
+ "\u2581\u043e": 540,
543
+ "\u2581pi": 541,
544
+ "\u2581inter": 542,
545
+ "tru": 543,
546
+ "\u2581ele": 544,
547
+ "\u062c": 545,
548
+ "\u2581\u03ba\u03b1\u03b9": 546,
549
+ "tti": 547,
550
+ "bra": 548,
551
+ "zione": 549,
552
+ "3": 550,
553
+ "Un": 551,
554
+ "l\u00e0": 552,
555
+ "\u00eatre": 553,
556
+ "\u2581esto": 554,
557
+ "\u0434\u043e": 555,
558
+ "En": 556,
559
+ "\u2581vida": 557,
560
+ "\u2581esse": 558,
561
+ "\u2581Ma": 559,
562
+ "\u043c\u0438": 560,
563
+ "ons": 561,
564
+ "\u03b1\u03bd": 562,
565
+ "\u0442\u0430": 563,
566
+ "\u2581emp": 564,
567
+ "\u2581parti": 565,
568
+ "ance": 566,
569
+ "tica": 567,
570
+ "\u2581ri": 568,
571
+ "\u03b5\u03af": 569,
572
+ "\u2581sono": 570,
573
+ "\u043c\u0430": 571,
574
+ "\u0440\u0438": 572,
575
+ "\u03b9\u03b1": 573,
576
+ "\u03cd": 574,
577
+ "\u2581faire": 575,
578
+ "\u2581fin": 576,
579
+ "\u043e\u0431": 577,
580
+ "\u2581mundo": 578,
581
+ "\u0434\u0438": 579,
582
+ "\u2581vie": 580,
583
+ "Q": 581,
584
+ "ation": 582,
585
+ "De": 583,
586
+ "\u2581cosa": 584,
587
+ "ient": 585,
588
+ "\u258120": 586,
589
+ "\u03b2": 587,
590
+ "\u043d\u0435": 588,
591
+ "\u2581li": 589,
592
+ "ber": 590,
593
+ "\u2581isso": 591,
594
+ "vers": 592,
595
+ "\u0435\u043c": 593,
596
+ "\u2581cor": 594,
597
+ "\u2581persona": 595,
598
+ "\u2581foi": 596,
599
+ "bre": 597,
600
+ "\u03c1\u03b1": 598,
601
+ "port": 599,
602
+ "\u2581entre": 600,
603
+ "\u0447\u0435": 601,
604
+ "\u2581moi": 602,
605
+ "\u2581\u043f\u0440\u043e": 603,
606
+ "\u2581essa": 604,
607
+ "bri": 605,
608
+ "l\u00e9": 606,
609
+ "nder": 607,
610
+ "\u2581sont": 608,
611
+ "cette": 609,
612
+ "a\u00e7\u00e3o": 610,
613
+ "\u0432\u0438": 611,
614
+ "U": 612,
615
+ "\u0627\u0644": 613,
616
+ "\u043a\u0438": 614,
617
+ "inte": 615,
618
+ "\u2581real": 616,
619
+ "\u060c": 617,
620
+ "\u2581exp": 618,
621
+ "\u0431\u043e": 619,
622
+ "\u2581sol": 620,
623
+ "\u2581col": 621,
624
+ "Que": 622,
625
+ "\u2581tiene": 623,
626
+ "encia": 624,
627
+ "\u2581voi": 625,
628
+ "\u2581pensa": 626,
629
+ "!\"": 627,
630
+ "\u2581\u043c\u043e": 628,
631
+ "r\u00eda": 629,
632
+ "\u00f1o": 630,
633
+ "tiva": 631,
634
+ "\u2581vol": 632,
635
+ "\u2581cap": 633,
636
+ "fica": 634,
637
+ "\u2581all": 635,
638
+ "\u2581peu": 636,
639
+ "\u00f1": 637,
640
+ "rie": 638,
641
+ "\u0635": 639,
642
+ "\u00f4": 640,
643
+ "B": 641,
644
+ "contr": 642,
645
+ "4": 643,
646
+ "\u2581qual": 644,
647
+ "\u2581\u0437\u0430": 645,
648
+ "\u2581vai": 646,
649
+ "\u2581questo": 647,
650
+ "\u0630": 648,
651
+ "mbi": 649,
652
+ "\u0634": 650,
653
+ "\u2581suis": 651,
654
+ "gio": 652,
655
+ "Si": 653,
656
+ "\u2581quando": 654,
657
+ "Se": 655,
658
+ "vent": 656,
659
+ "nza": 657,
660
+ "\u00e7o": 658,
661
+ "\u0447\u0430": 659,
662
+ "\u043c\u0443": 660,
663
+ "\"": 661,
664
+ "\u2581vez": 662,
665
+ "\u00bb": 663,
666
+ "v\u00e9": 664,
667
+ "\u0444": 665,
668
+ "nho": 666,
669
+ "\u2581pi\u00f9": 667,
670
+ "\u2014": 668,
671
+ "\u2581\"(": 669,
672
+ "prime": 670,
673
+ "\u2581minha": 671,
674
+ "\u2581peut": 672,
675
+ "\u2581\u0431\u044b": 673,
676
+ "\u2581hacer": 674,
677
+ "On": 675,
678
+ "\u03c1\u03bf": 676,
679
+ "\u03ba\u03b1": 677,
680
+ "Par": 678,
681
+ "00": 679,
682
+ "ntes": 680,
683
+ "cur": 681,
684
+ "9": 682,
685
+ "\u2581muy": 683,
686
+ "\u00e9tait": 684,
687
+ "\u2581grande": 685,
688
+ "\u00e2": 686,
689
+ "\u2581trans": 687,
690
+ "Com": 688,
691
+ "\u2581m\u00eame": 689,
692
+ "act": 690,
693
+ "\u2581fazer": 691,
694
+ "\u0418": 692,
695
+ "\u062e": 693,
696
+ "\u2581toda": 694,
697
+ "\u2581\u043a\u0430\u043a": 695,
698
+ "\u2581momento": 696,
699
+ "\u2581sobre": 697,
700
+ "\u2581n\u00f3s": 698,
701
+ "\u2581coisa": 699,
702
+ "\u03be": 700,
703
+ "\u0441\u0442\u0430": 701,
704
+ "8": 702,
705
+ "\u0637": 703,
706
+ "\u044d": 704,
707
+ "6": 705,
708
+ "\u03b6": 706,
709
+ "j": 707,
710
+ "\u00c9": 708,
711
+ "\u0446": 709,
712
+ "\u00f2": 710,
713
+ "W": 711,
714
+ "7": 712,
715
+ "\u041d": 713,
716
+ "\u0649": 714,
717
+ "%": 715,
718
+ "\u0412": 716,
719
+ "\u00f9": 717,
720
+ "\u062b": 718,
721
+ "\u00ec": 719,
722
+ "\u064b": 720,
723
+ "K": 721,
724
+ "\u0625": 722,
725
+ "\u00fc": 723,
726
+ "\u041f": 724,
727
+ "\u00ee": 725,
728
+ "\u0636": 726,
729
+ "[": 727,
730
+ "\u0421": 728,
731
+ "]": 729,
732
+ "\u041c": 730,
733
+ "\u039a": 731,
734
+ "\u00e4": 732,
735
+ "\u00a1": 733,
736
+ "\u0632": 734,
737
+ "\u266a": 735,
738
+ "\u00fb": 736,
739
+ "\u041a": 737,
740
+ "\u0391": 738,
741
+ "\u00e3": 739,
742
+ "\u0621": 740,
743
+ "\u0395": 741,
744
+ "\u00f5": 742,
745
+ "\u041e": 743,
746
+ "\u0422": 744,
747
+ "\u00bf": 745,
748
+ "\u063a": 746,
749
+ "\u042f": 747,
750
+ "\u03a4": 748,
751
+ "\u0410": 749,
752
+ "\u042d": 750,
753
+ "\u0414": 751,
754
+ "\u00f6": 752,
755
+ "\u0626": 753,
756
+ "\u00c8": 754,
757
+ "\u03a0": 755,
758
+ "\u0153": 756,
759
+ "X": 757,
760
+ "Z": 758,
761
+ "\u03c8": 759,
762
+ "\u039c": 760,
763
+ "\u03a3": 761,
764
+ "\u061f": 762,
765
+ "\u0651": 763,
766
+ "\u00c3": 764,
767
+ "\u0393": 765,
768
+ "\u0638": 766,
769
+ "\u201c": 767,
770
+ "\u201d": 768,
771
+ "\u0415": 769,
772
+ ">": 770,
773
+ "<": 771,
774
+ "/": 772,
775
+ "\u0394": 773,
776
+ "\u039f": 774,
777
+ "\u0388": 775,
778
+ "\u00ab": 776,
779
+ "\u00c0": 777,
780
+ "\u0427": 778,
781
+ "\u064f": 779,
782
+ "\u0411": 780,
783
+ "\u0423": 781,
784
+ "\u0417": 782,
785
+ "\u00df": 783,
786
+ "\u00e7": 784,
787
+ "\u0420": 785,
788
+ "\u0622": 786,
789
+ "\u00a9": 787,
790
+ "\u266b": 788,
791
+ "\u038c": 789,
792
+ "\u00ef": 790,
793
+ "q": 791,
794
+ "\u0397": 792,
795
+ "\u20ac": 793,
796
+ "\u039d": 794,
797
+ "\u0624": 795,
798
+ "\u0398": 796,
799
+ "\u2013": 797,
800
+ "\u041b": 798,
801
+ "\u03a7": 799,
802
+ "\u00c1": 800,
803
+ "\u0413": 801,
804
+ "\u0392": 802,
805
+ "\u039b": 803,
806
+ "\u064e": 804,
807
+ "\u0425": 805,
808
+ "\u0389": 806,
809
+ "\u03a6": 807,
810
+ "\u064d": 808,
811
+ "$": 809,
812
+ "\u03ca": 810,
813
+ "\u0399": 811,
814
+ "\u0386": 812,
815
+ "\u0424": 813,
816
+ "\u0301": 814,
817
+ "\u017d": 815,
818
+ "\u0650": 816,
819
+ "&": 817,
820
+ "\u0652": 818,
821
+ "\u03a5": 819,
822
+ "+": 820,
823
+ "\u00b0": 821,
824
+ "\u0428": 822,
825
+ "\u039e": 823,
826
+ "\u00eb": 824,
827
+ "\u0416": 825,
828
+ "\u064c": 826,
829
+ "\u03a1": 827,
830
+ "\u00ca": 828,
831
+ "\u0640": 829,
832
+ "\u2018": 830,
833
+ "\u00cd": 831,
834
+ "\u00d3": 832,
835
+ "\u2021": 833,
836
+ "\u0426": 834,
837
+ "\u061b": 835,
838
+ "\u03a9": 836,
839
+ "#": 837,
840
+ "(": 838,
841
+ "\u02c6": 839,
842
+ "\u00c2": 840,
843
+ "\u2039": 841,
844
+ "=": 842,
845
+ "\u042e": 843,
846
+ "\u00dc": 844,
847
+ "\u00d6": 845,
848
+ "\u00a7": 846,
849
+ "\u00d4": 847,
850
+ "\u06a8": 848,
851
+ "\u2015": 849,
852
+ "\u00da": 850,
853
+ "\u017c": 851,
854
+ "\u00e6": 852,
855
+ "*": 853,
856
+ "@": 854,
857
+ "\u04a3": 855,
858
+ "\u203a": 856,
859
+ "\u0303": 857,
860
+ "\u0456": 858,
861
+ "\u038f": 859,
862
+ "\u00a2": 860,
863
+ "\u2212": 861,
864
+ "\u04e9": 862,
865
+ "_": 863,
866
+ "\u00b7": 864,
867
+ "\u00fd": 865,
868
+ "\u00e5": 866,
869
+ "\u5bb6": 867,
870
+ "\u017e": 868,
871
+ "`": 869,
872
+ "\u025b": 870,
873
+ "\u0107": 871,
874
+ "\u0113": 872,
875
+ "\u0254": 873,
876
+ "\u201e": 874,
877
+ "\u00f8": 875,
878
+ "\u660e": 876,
879
+ "\u00ae": 877,
880
+ "\u00d1": 878,
881
+ "\u2030": 879,
882
+ "|": 880,
883
+ "\u014d": 881,
884
+ "\u01ce": 882,
885
+ "\u0400": 883,
886
+ "\u066a": 884,
887
+ "\u0219": 885,
888
+ "\u04b1": 886,
889
+ "\u049b": 887,
890
+ "\u529b": 888,
891
+ "\u0101": 889,
892
+ "}": 890,
893
+ "\u0115": 891,
894
+ "\u012b": 892,
895
+ "\u0142": 893,
896
+ "\u038e": 894,
897
+ "\u0662": 895,
898
+ "\u06f0": 896,
899
+ "\u010d": 897,
900
+ "\u0119": 898,
901
+ "\u00d7": 899,
902
+ "\u8c22": 900,
903
+ "\u52aa": 901,
904
+ "\u597d": 902,
905
+ "\u5929": 903,
906
+ "\u00a6": 904,
907
+ "\u011b": 905,
908
+ "\u0127": 906,
909
+ "\u016b": 907,
910
+ "\u03b0": 908,
911
+ "\u0429": 909,
912
+ "\u042b": 910,
913
+ "\u04af": 911,
914
+ "\u0663": 912,
915
+ "\u1eba": 913,
916
+ "\u4e50": 914,
917
+ "\u798f": 915,
918
+ "\u5927": 916,
919
+ "\u04bb": 917,
920
+ "\u00a3": 918,
921
+ "\u0493": 919,
922
+ "^": 920,
923
+ "\u1ebd": 921,
924
+ "\u2044": 922,
925
+ "\u014c": 923,
926
+ "\u00ce": 924,
927
+ "\u0419": 925,
928
+ "\u03a8": 926,
929
+ "\u03cb": 927,
930
+ "\u0390": 928,
931
+ "\u00c4": 929,
932
+ "\u0144": 930,
933
+ "\u0396": 931,
934
+ "\u038a": 932,
935
+ "\u0308": 933,
936
+ "\u044a": 934,
937
+ "\u00c7": 935,
938
+ "\u662f": 936,
939
+ "\u00c5": 937,
940
+ "\u1ff6": 938,
941
+ "\u221a": 939,
942
+ "\u6562": 940,
943
+ "\u1f14": 941,
944
+ "{": 942,
945
+ "~": 943,
946
+ "\u00d2": 944,
947
+ "\u0102": 945,
948
+ "\u0103": 946,
949
+ "\u010c": 947,
950
+ "\u0131": 948,
951
+ "\u0152": 949,
952
+ "\u015f": 950,
953
+ "\u0161": 951,
954
+ "\u016f": 952,
955
+ "\u0171": 953,
956
+ "\u0401": 954,
957
+ "\u049a": 955,
958
+ "\u04d9": 956,
959
+ "\u0661": 957,
960
+ "\u0666": 958,
961
+ "\u0671": 959,
962
+ "\u06f7": 960,
963
+ "\u1e47": 961,
964
+ "\u1f04": 962,
965
+ "\u1f50": 963,
966
+ "\u1f76": 964,
967
+ "\u1fc6": 965,
968
+ "\u2260": 966,
969
+ "\u2265": 967,
970
+ "\u4e22": 968,
971
+ "\u4e86": 969,
972
+ "\u4eca": 970,
973
+ "\u4eec": 971,
974
+ "\u4f60": 972,
975
+ "\u52c7": 973,
976
+ "\u5341": 974,
977
+ "\u5973": 975,
978
+ "\u5974": 976,
979
+ "\u5992": 977,
980
+ "\u5b50": 978,
981
+ "\u5b80": 979,
982
+ "\u5b89": 980,
983
+ "\u5b9e": 981,
984
+ "\u5c14": 982,
985
+ "\u5c81": 983,
986
+ "\u5e74": 984,
987
+ "\u5f97": 985,
988
+ "\u6211": 986,
989
+ "\u65e5": 987,
990
+ "\u6708": 988,
991
+ "\u732b": 989,
992
+ "\u7530": 990,
993
+ "\u7537": 991,
994
+ "\u7f8e": 992,
995
+ "\u8d1d": 993,
996
+ "\u8d23": 994,
997
+ "\u8d5b": 995,
998
+ "\u015b": 996,
999
+ "\u0178": 997,
1000
+ "\u0449": 998,
1001
+ "\u4e03": 999
1002
+ }