gsaltintas commited on
Commit
4184c32
·
verified ·
1 Parent(s): edbd452

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +5 -1
  2. special_tokens_map.json +0 -4
  3. tokenizer.json +29 -47
  4. tokenizer_config.json +0 -20
  5. vocab.json +375 -375
README.md CHANGED
@@ -47,4 +47,8 @@ tokens = tokenizer.encode("Hello, world!")
47
  ## Sample Encoding
48
  | Text | Tokens | Token IDs |
49
  |------|--------|-----------|
50
- | `yirmi iki+dokuz=otuz bir\ntwenty two+nine=thirty one` | `y, i, r, m, i, Ġ, i, k, i, +, d, o, k, u, z, =, o, t, u, z` | `91, 75, 84, 79, 75, 223, 75, 77, 75, 3, 70, 81, 77, 87, 92, 4, 81, 86, 87, 92` |
 
 
 
 
 
47
  ## Sample Encoding
48
  | Text | Tokens | Token IDs |
49
  |------|--------|-----------|
50
+ | `yirmi iki+dokuz=otuz bir\ntwenty two+nine=thirty one` | `y, i, r, m, i, Ġ, i, k, i, +, d, o, k, u, z, =, o, t, u, z` | `91, 75, 84, 79, 75, 223, 75, 77, 75, 13, 70, 81, 77, 87, 92, 31, 81, 86, 87, 92` |
51
+
52
+ Command used to create this tokenizer:
53
+ ```bash
54
+ ['/home/gsa/tokenizers2/flexitok/tokenizer_training/train_tokenizers.py', 'algorithm=bpe', 'vocab_size=2000', 'langs=[eng_Latn]', 'data_dir=/scratch/gsa/data/multilingual-addition/', 'output_dir=/scratch/gsa/trained_tokenizers/multilingual_addition', 'pretokenizer=custom:addition', 'number_handling=ltr_3digit', 'add_numbers=false', 'handle_contractions=false', 'unicode_normalization=nfc', 'use_byte_level_regex=false', 'byte_fallback=false', 'strip_zero_width=false', 'cjk_char_split=false', 'add_cjk_chars=false', 'max_lines=-1', 'test_string=yirmi iki+dokuz=otuz bir\\ntwenty two+nine=thirty one', 'hf.publish_to_hf=true', 'hf_repo_prefix=flexitok/', 'hf.hf_repo_id=flexitok/maddition_eng_Latn_2000', 'hf.collections=[flexitok/multilingual_addition_tokenizers]']
special_tokens_map.json CHANGED
@@ -1,8 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "+",
4
- "="
5
- ],
6
  "bos_token": "<s>",
7
  "eos_token": "</s>",
8
  "pad_token": "<pad>"
 
1
  {
 
 
 
 
2
  "bos_token": "<s>",
3
  "eos_token": "</s>",
4
  "pad_token": "<pad>"
tokenizer.json CHANGED
@@ -29,24 +29,6 @@
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
- },
33
- {
34
- "id": 3,
35
- "content": "+",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": false,
40
- "special": true
41
- },
42
- {
43
- "id": 4,
44
- "content": "=",
45
- "single_word": false,
46
- "lstrip": false,
47
- "rstrip": false,
48
- "normalized": false,
49
- "special": true
50
  }
51
  ],
52
  "normalizer": {
@@ -99,35 +81,35 @@
99
  "<s>": 0,
100
  "</s>": 1,
101
  "<pad>": 2,
102
- "+": 3,
103
- "=": 4,
104
- "!": 5,
105
- "\"": 6,
106
- "#": 7,
107
- "$": 8,
108
- "%": 9,
109
- "&": 10,
110
- "'": 11,
111
- "(": 12,
112
- ")": 13,
113
- "*": 14,
114
- ",": 15,
115
- "-": 16,
116
- ".": 17,
117
- "/": 18,
118
- "0": 19,
119
- "1": 20,
120
- "2": 21,
121
- "3": 22,
122
- "4": 23,
123
- "5": 24,
124
- "6": 25,
125
- "7": 26,
126
- "8": 27,
127
- "9": 28,
128
- ":": 29,
129
- ";": 30,
130
- "<": 31,
131
  ">": 32,
132
  "?": 33,
133
  "@": 34,
 
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
 
81
  "<s>": 0,
82
  "</s>": 1,
83
  "<pad>": 2,
84
+ "!": 3,
85
+ "\"": 4,
86
+ "#": 5,
87
+ "$": 6,
88
+ "%": 7,
89
+ "&": 8,
90
+ "'": 9,
91
+ "(": 10,
92
+ ")": 11,
93
+ "*": 12,
94
+ "+": 13,
95
+ ",": 14,
96
+ "-": 15,
97
+ ".": 16,
98
+ "/": 17,
99
+ "0": 18,
100
+ "1": 19,
101
+ "2": 20,
102
+ "3": 21,
103
+ "4": 22,
104
+ "5": 23,
105
+ "6": 24,
106
+ "7": 25,
107
+ "8": 26,
108
+ "9": 27,
109
+ ":": 28,
110
+ ";": 29,
111
+ "<": 30,
112
+ "=": 31,
113
  ">": 32,
114
  "?": 33,
115
  "@": 34,
tokenizer_config.json CHANGED
@@ -23,28 +23,8 @@
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
- },
27
- "3": {
28
- "content": "+",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "4": {
36
- "content": "=",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
  }
43
  },
44
- "additional_special_tokens": [
45
- "+",
46
- "="
47
- ],
48
  "bos_token": "<s>",
49
  "clean_up_tokenization_spaces": false,
50
  "eos_token": "</s>",
 
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  }
27
  },
 
 
 
 
28
  "bos_token": "<s>",
29
  "clean_up_tokenization_spaces": false,
30
  "eos_token": "</s>",
vocab.json CHANGED
@@ -1,411 +1,411 @@
1
  {
2
- "÷": 182,
3
- "gh": 277,
4
- "ninety-one": 332,
5
- "n": 80,
6
- "[": 61,
7
- ">": 32,
8
- "sixty-four": 355,
9
- "¢": 98,
10
- "ve": 269,
11
- "seventy-eight": 345,
12
  "seventy-six": 344,
13
- "x": 90,
14
- "fifty-": 307,
15
- "ĩ": 232,
16
- ")": 13,
17
- "fifty-one": 377,
18
- "Ľ": 252,
19
- "IJ": 241,
20
- "¥": 101,
21
- "H": 42,
22
- "é": 168,
23
- "ä": 163,
24
  "W": 57,
25
- "5": 24,
26
- "ix": 278,
27
- "z": 92,
28
- "ę": 216,
29
- "S": 53,
30
  "eighty-eight": 363,
 
 
 
 
 
 
 
 
31
  "ø": 183,
32
- "Ý": 156,
33
- "ninety-eight": 336,
34
- "Ã": 130,
35
- "ý": 188,
 
 
 
 
 
 
36
  "ij": 242,
37
- "ı": 240,
38
- "ç": 166,
39
- "³": 114,
40
- "four": 287,
41
- "l": 78,
42
- "Ğ": 221,
43
- "J": 44,
44
- "sixteen": 321,
45
- "Ď": 205,
46
- "re": 260,
47
- "nine": 280,
48
- "ninety-two": 340,
49
- "K": 45,
50
- "0": 19,
51
- "ĺ": 249,
52
- "Ģ": 225,
53
- "eleven": 404,
54
- "thousand": 296,
55
- "ninety-": 302,
56
- "twel": 322,
57
- "sixty": 320,
58
- "ou": 271,
59
- "thousand,": 297,
60
- "!": 5,
61
- "à": 159,
62
- "+": 3,
63
- "ł": 257,
64
- "Ĩ": 231,
65
- "thirty-": 306,
66
- "nd": 259,
67
- "Ć": 197,
68
- "¸": 119,
69
- "rty-": 293,
70
- "@": 34,
71
- "$": 8,
72
- "ć": 198,
73
- "ty-": 267,
74
- "g": 73,
75
- "8": 27,
76
- "five": 290,
77
- "eighty-": 305,
78
- "fif": 299,
79
- "ė": 214,
80
- "Ñ": 144,
81
- "ei": 275,
82
- "ninety-nine": 333,
83
- "ē": 210,
84
- "k": 77,
85
- "sixty-nine": 351,
86
- "eve": 273,
87
- "six": 282,
88
- "Ô": 147,
89
- "Ŀ": 254,
90
- "Ń": 258,
91
- "thirty": 326,
92
- "forty-six": 389,
93
- "q": 83,
94
- "É": 136,
95
- "9": 28,
96
- "§": 103,
97
- "/": 18,
98
- "C": 37,
99
- "sixty-six": 353,
100
  "eighty-five": 366,
101
- "thirty-eight": 372,
102
- "Į": 237,
103
- "Ĉ": 199,
104
- "sixty-five": 357,
105
- "ð": 175,
106
- "fifty-seven": 379,
107
- "fifty-two": 385,
108
  "Å": 132,
109
- "ninety-four": 337,
110
- "three": 289,
111
- "×": 150,
112
- "û": 186,
113
- "ľ": 253,
114
- "ne": 268,
115
- "Ç": 134,
116
- "ten": 315,
117
- "thirteen": 327,
118
- "½": 124,
119
- "teen": 311,
120
- "d": 70,
121
- "}": 95,
122
- "seven": 281,
123
- "Ó": 146,
124
- "i": 75,
125
- "ħ": 230,
126
- "4": 23,
127
- "w": 89,
128
- "fifty-eight": 381,
129
- "seventy": 318,
130
- "twenty-": 309,
131
- "a": 67,
132
- "=": 4,
133
- "sixty-one": 350,
134
- "Ò": 145,
135
- "I": 43,
136
- "¹": 120,
137
- "G": 41,
138
- "th": 270,
139
- "Q": 51,
140
- "eighty": 323,
141
- "b": 68,
142
- "Þ": 157,
143
- "zer": 407,
144
- "forty-five": 393,
145
- "Ē": 209,
146
- "\\": 62,
147
- "¨": 104,
148
  "¡": 97,
149
- "·": 118,
150
- "fi": 276,
151
- "ü": 187,
152
- "ĵ": 244,
153
- "ninety-five": 339,
154
- "¿": 126,
155
- "ĸ": 247,
156
- "6": 25,
157
- "¬": 108,
158
- "er": 406,
159
- "U": 55,
160
- "7": 26,
161
- "*": 14,
162
- "twelve": 405,
163
- "ą": 196,
164
- "Ļ": 250,
165
- "thirty-seven": 370,
166
- "fifty-six": 380,
167
- "ß": 158,
168
- "«": 107,
169
- "ó": 178,
170
- "ě": 218,
171
- "twenty-nine": 396,
172
- "ñ": 176,
173
- ";": 30,
174
- "sixty-three": 356,
175
- "|": 94,
176
- "f": 72,
177
- "Ĭ": 235,
178
- "å": 164,
179
- "È": 135,
180
- "Ī": 233,
181
- "v": 88,
182
- "rteen": 314,
183
- "hu": 262,
184
- "ì": 171,
185
  "u": 87,
186
- "thou": 295,
187
- "č": 204,
188
- "seventy-": 303,
189
- "eight": 286,
190
- "tw": 283,
191
  "Ę": 215,
192
- "seventy-five": 348,
193
- ".": 17,
194
- "T": 54,
195
- "": 117,
 
 
 
 
 
196
  "ty": 266,
197
- "õ": 180,
198
- "Ĵ": 243,
199
- "<pad>": 2,
200
- "]": 63,
201
- "fifty-five": 384,
202
- "æ": 165,
203
- "Ā": 191,
204
- "thirty-six": 371,
205
- "B": 36,
206
  "r": 84,
207
- "c": 69,
208
- "Ð": 143,
209
- "'": 11,
 
 
 
 
 
 
 
210
  "¯": 110,
211
- "ninety-three": 338,
212
- "fourteen": 325,
213
- "ķ": 246,
214
- "Y": 59,
215
- "À": 127,
216
- "î": 173,
217
- "1": 20,
218
  "á": 160,
219
- "hundred": 265,
220
- "Ĥ": 227,
221
- "\"": 6,
222
- "t": 86,
223
- "Ķ": 245,
224
- "Ċ": 201,
225
- "Ġ": 223,
226
- "M": 47,
227
- "ļ": 251,
228
- "twenty": 331,
229
- "twenty-six": 398,
230
- "ĕ": 212,
231
- "ù": 184,
232
- "ď": 206,
233
  "eigh": 284,
234
- "sixty-two": 358,
 
 
 
 
235
  "ninety-seven": 334,
236
- "thi": 298,
237
- "®": 109,
238
- "İ": 239,
239
- "fifty": 328,
240
- "ê": 169,
241
- "º": 121,
242
- "h": 74,
243
- "±": 112,
244
- "two": 291,
245
- "đ": 208,
246
- "ö": 181,
247
- "ā": 192,
248
- "ª": 106,
249
- "Ă": 193,
250
- "forty-two": 394,
251
- "Đ": 207,
252
- "thirty-nine": 369,
253
- "ï": 174,
254
- "thirty-four": 373,
255
- "forty-nine": 387,
256
- "ë": 170,
257
- "%": 9,
258
- "sixty-seven": 352,
259
- "Ù": 152,
260
- ",": 15,
261
- "Ě": 217,
262
- "rty": 313,
263
- "forty-three": 392,
264
- "Â": 129,
265
- "forty-one": 386,
266
- "©": 105,
267
  "Ë": 138,
268
- "D": 38,
 
 
 
 
 
 
 
 
 
 
 
 
269
  "seventy-seven": 343,
270
- "Ø": 151,
271
- "´": 115,
272
- "twenty-five": 402,
273
- ":": 29,
274
- "#": 7,
275
- "<s>": 0,
276
- "¦": 102,
277
- "eighty-two": 367,
278
- "ninety": 316,
279
- "°": 111,
280
- "y": 91,
281
- "-": 16,
282
- "fo": 300,
283
- "V": 56,
284
- "ine": 279,
285
- "eighty-six": 362,
286
  "į": 238,
287
- "ô": 179,
288
- "Ĕ": 211,
289
- "seventeen": 319,
290
- "ğ": 222,
291
- "one": 272,
292
- "Ä": 131,
293
- "Õ": 148,
294
- "~": 96,
295
- "è": 167,
296
- "Ï": 142,
297
- "L": 46,
298
- "twenty-four": 400,
299
- "fifteen": 329,
300
- "P": 50,
301
- "Á": 128,
302
  "seventy-one": 341,
303
- "(": 12,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  "þ": 189,
305
- "fifty-four": 382,
306
- "ī": 234,
307
- "zero": 408,
308
  "Í": 140,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
309
  "e": 71,
310
- "thirty-two": 376,
311
- "F": 40,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
312
  "ninety-six": 335,
313
- "Ĝ": 219,
314
- "fifty-three": 383,
315
- "sixty-": 304,
316
- "ŀ": 255,
317
- "{": 93,
318
- "ģ": 226,
319
- "eighteen": 324,
320
- "sixty-eight": 354,
321
- "ndre": 263,
322
- "seventy-two": 349,
323
- "even": 274,
324
- "forty": 330,
325
- "E": 39,
326
- "X": 58,
327
  "²": 113,
328
- "and": 261,
329
- "Û": 154,
330
- "O": 49,
331
- "p": 82,
332
- "een": 310,
333
- "Z": 60,
334
- "twen": 301,
335
- "N": 48,
336
- "Č": 203,
337
- "sand": 294,
338
  "Ü": 155,
339
- "<": 31,
340
- "ĉ": 200,
341
- "í": 172,
342
- "ã": 162,
343
- "seventy-three": 347,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
344
  "twenty-eight": 399,
345
- "nineteen": 317,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
346
  "eighty-seven": 361,
347
- "ċ": 202,
348
- "Ö": 149,
349
- "twenty-three": 401,
350
- "eighty-three": 365,
 
 
 
 
351
  "Ú": 153,
352
- "µ": 116,
353
- "&": 10,
354
- "R": 52,
355
- "el": 312,
356
- "s": 85,
357
- "eighty-one": 359,
358
- "Ì": 139,
 
 
 
 
 
 
 
 
 
359
  "ĭ": 236,
360
- "Ħ": 229,
361
- "¼": 123,
362
- "thirty-three": 374,
363
- "ĥ": 228,
364
- "thirty-one": 368,
365
- "j": 76,
366
- "3": 22,
367
- "Ą": 195,
368
- "Æ": 133,
369
- "¾": 125,
370
- "fifty-nine": 378,
371
- "ree": 288,
372
- "hundre": 264,
373
- "â": 161,
374
- "_": 65,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
375
  "A": 35,
376
- "¤": 100,
377
- "forty-": 308,
378
- "Ê": 137,
379
- "ġ": 224,
380
- "eighty-four": 364,
381
- "twenty-one": 395,
 
 
 
 
 
 
 
 
 
 
 
 
 
382
  "forty-eight": 390,
383
- "seventy-four": 346,
384
- "o": 81,
385
- "eighty-nine": 360,
386
- "Ł": 256,
387
- "ÿ": 190,
388
- "m": 79,
389
- "2": 21,
390
- "ú": 185,
391
  "£": 99,
392
- "Î": 141,
393
- "^": 64,
394
- "ĝ": 220,
395
- "twenty-two": 403,
396
- "Ĺ": 248,
397
- "forty-seven": 388,
398
- "ă": 194,
399
- "»": 122,
400
- "ò": 177,
401
- "twenty-seven": 397,
402
- "thirty-five": 375,
403
- "en": 292,
404
- "`": 66,
405
- "seventy-nine": 342,
406
- "?": 33,
407
- "</s>": 1,
408
- "forty-four": 391,
 
 
 
 
 
 
409
  "fou": 285,
410
- "Ė": 213
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
411
  }
 
1
  {
2
+ "a": 67,
3
+ "ļ": 251,
4
+ "?": 33,
5
+ "thirty-four": 373,
6
+ "hu": 262,
7
+ "seventy-three": 347,
8
+ "U": 55,
 
 
 
9
  "seventy-six": 344,
10
+ "thirty-one": 368,
 
 
 
 
 
 
 
 
 
 
11
  "W": 57,
12
+ "í": 172,
13
+ "three": 289,
14
+ "thirty-": 306,
15
+ "<": 30,
 
16
  "eighty-eight": 363,
17
+ "`": 66,
18
+ "gh": 277,
19
+ "ninety-nine": 333,
20
+ "ñ": 176,
21
+ "Ĉ": 199,
22
+ "</s>": 1,
23
+ "forty-four": 391,
24
+ "th": 270,
25
  "ø": 183,
26
+ "Ù": 152,
27
+ "forty-seven": 388,
28
+ "ħ": 230,
29
+ "fifty-one": 377,
30
+ "fifteen": 329,
31
+ "Č": 203,
32
+ "ninety-four": 337,
33
+ "ô": 179,
34
+ "eighty-three": 365,
35
+ "{": 93,
36
  "ij": 242,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "eighty-five": 366,
38
+ "ě": 218,
39
+ "[": 61,
40
+ "p": 82,
41
+ "2": 20,
42
+ "4": 22,
43
+ "·": 118,
44
+ "forty-": 308,
45
  "Å": 132,
46
+ "V": 56,
47
+ "g": 73,
48
+ "ve": 269,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  "¡": 97,
50
+ "ÿ": 190,
51
+ "twenty-seven": 397,
52
+ "ty-": 267,
53
+ "eighty-two": 367,
54
+ "Ð": 143,
55
+ "Ď": 205,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  "u": 87,
57
+ "Ļ": 250,
 
 
 
 
58
  "Ę": 215,
59
+ "q": 83,
60
+ "×": 150,
61
+ "X": 58,
62
+ "Ì": 139,
63
+ ":": 28,
64
+ "thirty-eight": 372,
65
+ "nd": 259,
66
+ "Î": 141,
67
+ "ï": 174,
68
  "ty": 266,
69
+ "Ă": 193,
70
+ "t": 86,
71
+ "fifty-three": 383,
72
+ "$": 6,
 
 
 
 
 
73
  "r": 84,
74
+ "ö": 181,
75
+ "thirty-three": 374,
76
+ "twenty-two": 403,
77
+ "¾": 125,
78
+ "Æ": 133,
79
+ "twenty-five": 402,
80
+ "/": 17,
81
+ "ä": 163,
82
+ "n": 80,
83
+ "Ĥ": 227,
84
  "¯": 110,
85
+ "½": 124,
86
+ "Ĭ": 235,
87
+ "Ä": 131,
88
+ "%": 7,
89
+ "ninety-two": 340,
90
+ "ĩ": 232,
 
91
  "á": 160,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
  "eigh": 284,
93
+ "sixty-four": 355,
94
+ "fifty-": 307,
95
+ "sixty-nine": 351,
96
+ "ą": 196,
97
+ "sixty-one": 350,
98
  "ninety-seven": 334,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  "Ë": 138,
100
+ "<pad>": 2,
101
+ "seventy": 318,
102
+ "ì": 171,
103
+ "Ï": 142,
104
+ "ou": 271,
105
+ "ğ": 222,
106
+ "¤": 100,
107
+ "twelve": 405,
108
+ "-": 15,
109
+ "rteen": 314,
110
+ "en": 292,
111
+ "er": 406,
112
+ "æ": 165,
113
  "seventy-seven": 343,
114
+ "©": 105,
115
+ "j": 76,
116
+ "R": 52,
 
 
 
 
 
 
 
 
 
 
 
 
 
117
  "į": 238,
118
+ "fourteen": 325,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
119
  "seventy-one": 341,
120
+ "à": 159,
121
+ "å": 164,
122
+ "sixty-three": 356,
123
+ "thi": 298,
124
+ "ã": 162,
125
+ "G": 41,
126
+ "teen": 311,
127
+ "ē": 210,
128
+ "ó": 178,
129
+ "hundre": 264,
130
+ ";": 29,
131
+ "ninety-three": 338,
132
+ "K": 45,
133
+ "forty-six": 389,
134
+ "Ĝ": 219,
135
+ "ċ": 202,
136
+ "¢": 98,
137
+ "ł": 257,
138
+ "thirty": 326,
139
+ "8": 26,
140
+ "¥": 101,
141
+ "twenty-one": 395,
142
+ "seventy-five": 348,
143
+ "=": 31,
144
+ "÷": 182,
145
  "þ": 189,
 
 
 
146
  "Í": 140,
147
+ "seventy-four": 346,
148
+ "Ģ": 225,
149
+ "fi": 276,
150
+ "zero": 408,
151
+ "_": 65,
152
+ "ç": 166,
153
+ "tw": 283,
154
+ "ĵ": 244,
155
+ "Ľ": 252,
156
+ "ģ": 226,
157
+ "Ø": 151,
158
+ ",": 14,
159
+ "#": 5,
160
+ "3": 21,
161
+ "seventeen": 319,
162
+ "*": 12,
163
+ "ninety": 316,
164
+ "sixty": 320,
165
+ "6": 24,
166
+ "fifty-eight": 381,
167
+ "+": 13,
168
+ "thirteen": 327,
169
+ "fifty-nine": 378,
170
+ "Į": 237,
171
+ "rty": 313,
172
+ "&": 8,
173
+ "î": 173,
174
+ "thirty-five": 375,
175
+ "İ": 239,
176
+ "C": 37,
177
+ "forty-one": 386,
178
+ "ß": 158,
179
  "e": 71,
180
+ "č": 204,
181
+ "h": 74,
182
+ "eighty-four": 364,
183
+ "Ô": 147,
184
+ ")": 11,
185
+ "ú": 185,
186
+ "ā": 192,
187
+ "<s>": 0,
188
+ "twenty": 331,
189
+ "J": 44,
190
+ "twenty-nine": 396,
191
+ "7": 25,
192
+ "eighty-": 305,
193
+ "Ą": 195,
194
+ "M": 47,
195
+ "¬": 108,
196
+ "fifty-six": 380,
197
+ "1": 19,
198
+ "µ": 116,
199
+ "sixty-six": 353,
200
+ "H": 42,
201
  "ninety-six": 335,
202
+ "Ĩ": 231,
203
+ "seventy-nine": 342,
204
+ "S": 53,
205
+ "ī": 234,
206
+ "Ń": 258,
207
+ "sixty-five": 357,
208
+ "ķ": 246,
209
+ "forty-nine": 387,
210
+ "ĉ": 200,
211
+ "®": 109,
 
 
 
 
212
  "²": 113,
213
+ "ý": 188,
214
+ "y": 91,
215
+ "": 117,
 
 
 
 
 
 
 
216
  "Ü": 155,
217
+ "Ê": 137,
218
+ "x": 90,
219
+ "Ò": 145,
220
+ "rty-": 293,
221
+ "forty-three": 392,
222
+ "ĥ": 228,
223
+ "§": 103,
224
+ "thousand": 296,
225
+ "thou": 295,
226
+ "eighty-nine": 360,
227
+ "ď": 206,
228
+ "¼": 123,
229
+ "5": 23,
230
+ "sixty-eight": 354,
231
+ "ninety-eight": 336,
232
+ "ă": 194,
233
+ "Ã": 130,
234
+ "F": 40,
235
+ "@": 34,
236
+ "Á": 128,
237
+ "O": 49,
238
+ "re": 260,
239
+ "Ī": 233,
240
+ "ð": 175,
241
+ "´": 115,
242
+ "w": 89,
243
+ "ei": 275,
244
+ "Ĺ": 248,
245
+ "Â": 129,
246
+ "four": 287,
247
+ "³": 114,
248
+ "twel": 322,
249
+ "z": 92,
250
+ "thirty-two": 376,
251
+ "d": 70,
252
+ "fifty-five": 384,
253
+ "ġ": 224,
254
+ "Ě": 217,
255
+ "thousand,": 297,
256
+ "Ĵ": 243,
257
+ "fifty": 328,
258
+ "Õ": 148,
259
+ "fif": 299,
260
+ "hundred": 265,
261
+ "sixty-two": 358,
262
+ "five": 290,
263
+ "seventy-": 303,
264
+ "s": 85,
265
+ "ı": 240,
266
+ "ë": 170,
267
  "twenty-eight": 399,
268
+ "een": 310,
269
+ "fifty-two": 385,
270
+ "and": 261,
271
+ "o": 81,
272
+ "Ē": 209,
273
+ "eight": 286,
274
+ "«": 107,
275
+ "Q": 51,
276
+ "ten": 315,
277
+ "ė": 214,
278
+ "(": 10,
279
+ "sixteen": 321,
280
+ "ree": 288,
281
+ "ŀ": 255,
282
+ ">": 32,
283
+ "^": 64,
284
+ "i": 75,
285
  "eighty-seven": 361,
286
+ "twenty-four": 400,
287
+ "thirty-six": 371,
288
+ "]": 63,
289
+ "Ý": 156,
290
+ "¿": 126,
291
+ "forty-two": 394,
292
+ "}": 95,
293
+ "»": 122,
294
  "Ú": 153,
295
+ "Đ": 207,
296
+ "L": 46,
297
+ "D": 38,
298
+ "è": 167,
299
+ "ľ": 253,
300
+ "twenty-six": 398,
301
+ "Z": 60,
302
+ "Ŀ": 254,
303
+ "º": 121,
304
+ "m": 79,
305
+ "Ġ": 223,
306
+ "ü": 187,
307
+ "nineteen": 317,
308
+ "forty-five": 393,
309
+ "ĺ": 249,
310
+ "é": 168,
311
  "ĭ": 236,
312
+ "|": 94,
313
+ "ninety-": 302,
314
+ "Ł": 256,
315
+ "ù": 184,
316
+ "¨": 104,
317
+ "0": 18,
318
+ "two": 291,
319
+ "six": 282,
320
+ "Y": 59,
321
+ "fifty-four": 382,
322
+ "k": 77,
323
+ "E": 39,
324
+ "I": 43,
325
+ "IJ": 241,
326
+ "twen": 301,
327
+ "ninety-one": 332,
328
+ "ò": 177,
329
+ "ę": 216,
330
+ "\\": 62,
331
+ "nine": 280,
332
+ "±": 112,
333
+ "ix": 278,
334
+ "eighteen": 324,
335
+ "û": 186,
336
+ "thirty-nine": 369,
337
+ "twenty-": 309,
338
+ "Ç": 134,
339
+ "c": 69,
340
+ "v": 88,
341
+ "seventy-two": 349,
342
  "A": 35,
343
+ "ć": 198,
344
+ "twenty-three": 401,
345
+ "ndre": 263,
346
+ "É": 136,
347
+ "9": 27,
348
+ "zer": 407,
349
+ "°": 111,
350
+ "l": 78,
351
+ "Ñ": 144,
352
+ "Ö": 149,
353
+ "B": 36,
354
+ "¹": 120,
355
+ "eighty": 323,
356
+ "đ": 208,
357
+ "!": 3,
358
+ "even": 274,
359
+ "seventy-eight": 345,
360
+ "¦": 102,
361
+ "Ğ": 221,
362
  "forty-eight": 390,
363
+ "one": 272,
 
 
 
 
 
 
 
364
  "£": 99,
365
+ "Ĕ": 211,
366
+ "b": 68,
367
+ "Ć": 197,
368
+ "Ó": 146,
369
+ "Ċ": 201,
370
+ "el": 312,
371
+ "eleven": 404,
372
+ "'": 9,
373
+ "sixty-seven": 352,
374
+ "T": 54,
375
+ "Û": 154,
376
+ "ne": 268,
377
+ "ĸ": 247,
378
+ "seven": 281,
379
+ "¸": 119,
380
+ "sand": 294,
381
+ "~": 96,
382
+ "ê": 169,
383
+ "\"": 4,
384
+ "thirty-seven": 370,
385
+ ".": 16,
386
+ "fifty-seven": 379,
387
+ "Ħ": 229,
388
  "fou": 285,
389
+ "ĝ": 220,
390
+ "À": 127,
391
+ "ine": 279,
392
+ "Ė": 213,
393
+ "f": 72,
394
+ "fo": 300,
395
+ "õ": 180,
396
+ "ninety-five": 339,
397
+ "eve": 273,
398
+ "eighty-one": 359,
399
+ "sixty-": 304,
400
+ "È": 135,
401
+ "Þ": 157,
402
+ "â": 161,
403
+ "forty": 330,
404
+ "N": 48,
405
+ "P": 50,
406
+ "Ķ": 245,
407
+ "eighty-six": 362,
408
+ "ª": 106,
409
+ "Ā": 191,
410
+ "ĕ": 212
411
  }