gsaltintas commited on
Commit
e6b1ac0
·
verified ·
1 Parent(s): e1bbc9d

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 +315 -315
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=[pol_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_pol_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
@@ -1,348 +1,348 @@
1
  {
2
- "Ĩ": 231,
3
- "ç": 166,
4
- "Į": 237,
5
- "5": 24,
6
- "Z": 60,
7
- "trzysta": 314,
8
- "\"": 6,
9
- "Ł": 256,
10
- "q": 83,
11
- "Ñ": 144,
12
- "ieÅĽcie": 307,
13
- "dziewiÄĻtnaÅĽcie": 335,
14
- "Ħ": 229,
15
- ",": 15,
16
- "Ö": 149,
17
- "e": 71,
18
- "ÿ": 190,
19
- "ÅĽc": 274,
20
- "Ð": 143,
21
- "1": 20,
22
- "</s>": 1,
23
- "¨": 104,
24
- "cz": 277,
25
- "Ď": 205,
26
- "Ķ": 245,
27
- "0": 19,
28
- "P": 50,
29
  "jede": 306,
30
- "å": 164,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  "szeÅĽÄĩdziesiÄħt": 323,
32
- "jeden": 326,
33
- "ă": 194,
34
- "czterdzieÅĽci": 310,
35
- "ter": 283,
36
- "dzieÅĽc": 286,
37
- "G": 41,
38
- "r": 84,
39
- "dziesiÄ": 334,
40
- "þ": 189,
41
- "siedem": 293,
42
- "'": 11,
43
  "ô": 179,
44
- "Ç": 134,
45
- "Ã": 130,
46
- "sze": 290,
47
- "dziewiÄĻÄĩset": 320,
48
- "×": 150,
 
 
 
 
 
 
 
49
  "L": 46,
50
- "osiem": 289,
51
- "Ä": 131,
52
- "¹": 120,
53
  "Ê": 137,
54
- "¦": 102,
55
- "T": 54,
56
- "czter": 288,
57
- "©": 105,
58
- "siÄħc": 303,
59
- "j": 76,
60
- "piÄĻÄĩ": 294,
61
- "²": 113,
62
- "\\": 62,
63
- "zero": 345,
64
- "ty": 302,
65
- "Ô": 147,
 
 
 
 
 
 
 
 
 
 
 
66
  "Õ": 148,
67
- "de": 275,
 
 
 
 
 
 
68
  "osiemset": 311,
69
- "ĩ": 232,
70
- "Þ": 157,
71
- "Ċ": 201,
72
- "»": 122,
73
- "piÄĻÄĩset": 318,
74
- "î": 173,
75
  "Ì": 139,
76
- "sie": 267,
77
- "Ú": 153,
78
- "_": 65,
79
- "Ī": 233,
80
- "dwieÅĽcie": 308,
81
- "È": 135,
82
- "k": 77,
83
- ".": 17,
84
- "«": 107,
85
- "Ĥ": 227,
86
- "+": 3,
87
- "&": 10,
88
  "F": 40,
89
- "ü": 187,
90
- "set": 271,
91
- "b": 68,
92
- "siedemdziesiÄħt": 317,
93
- "trzy": 291,
94
- "czterysta": 325,
95
- "szesnaÅĽcie": 338,
96
- "Ć": 197,
97
- "K": 45,
98
- "x": 90,
99
- "¥": 101,
100
- "dwadzieÅĽcia": 324,
101
  "ĸ": 247,
102
- "Đ": 207,
103
- "Č": 203,
104
- ">": 32,
105
- ")": 13,
106
- "ē": 210,
107
- "h": 74,
108
- "¢": 98,
109
- "đ": 208,
110
- "Ó": 146,
111
- "Ë": 138,
112
- "À": 127,
113
- "v": 88,
114
- "·": 118,
115
- "d": 70,
116
- "ï": 174,
117
- "N": 48,
118
- "f": 72,
119
- "ĝ": 220,
120
- "Ĭ": 235,
121
- "$": 8,
122
- "o": 81,
123
- "¸": 119,
124
- "¡": 97,
125
- "ÅĽ": 264,
126
- "é": 168,
127
- "~": 96,
128
- "I": 43,
129
- "n": 80,
130
- "er": 276,
131
- "a": 67,
132
- "ã": 162,
133
- "<": 31,
134
- "l": 78,
135
- "osiemdziesiÄħt": 312,
136
- "â": 161,
137
- "ÅĽÄĩ": 295,
138
- "dwanaÅĽcie": 341,
139
- "R": 52,
140
  "á": 160,
141
- "S": 53,
142
- "siÄ": 265,
143
- "ĭ": 236,
144
- "H": 42,
145
- "V": 56,
146
- "E": 39,
147
- "¼": 123,
148
- "<s>": 0,
149
- "ê": 169,
150
- "8": 27,
151
- "J": 44,
152
- "dzie": 262,
153
- "U": 55,
154
- "Ń": 258,
155
- "jedenaÅĽcie": 342,
156
  "Ġ": 223,
157
- "ą": 196,
158
- "ä": 163,
159
- "c": 69,
160
- "ď": 206,
161
- "cztery": 301,
162
- "Y": 59,
163
- "": 117,
164
- "X": 58,
165
- "Ă": 193,
166
- "7": 26,
167
- "¯": 110,
168
- "iÄĻ": 268,
169
- "±": 112,
 
 
 
 
 
 
 
 
 
 
 
 
170
  "?": 33,
171
- "C": 37,
172
- "IJ": 241,
173
- "osie": 279,
174
- "°": 111,
175
- "snaÅĽcie": 332,
176
- "¾": 125,
 
177
  "ð": 175,
178
- "ie": 259,
179
- "Ŀ": 254,
180
- "ě": 218,
181
- "ù": 184,
182
- "`": 66,
183
- "ĻÄĩ": 333,
184
- "ø": 183,
185
- "}": 95,
186
- "Ï": 142,
187
- "p": 82,
188
- "ú": 185,
 
 
 
 
 
 
 
189
  "sz": 282,
190
- "Å": 132,
191
- "Ē": 209,
192
- "û": 186,
193
- "dwa": 298,
194
- "£": 99,
195
- "º": 121,
196
- "Ý": 156,
197
- "dziewiÄĻÄĩ": 296,
198
- "ĕ": 212,
199
- "[": 61,
200
- "ĺ": 249,
201
- "4": 23,
202
- "Î": 141,
203
- "ġ": 224,
204
- "İ": 239,
205
- "(": 12,
206
- "@": 34,
207
- "trz": 284,
208
- "ª": 106,
209
- "Ĺ": 248,
210
- "z": 92,
211
  "¿": 126,
212
- "ĵ": 244,
213
- "ę": 216,
214
- "*": 14,
215
- "ĥ": 228,
216
- "ļ": 251,
217
- "szeÅĽÄĩset": 322,
218
- "et": 270,
219
- "ł": 257,
220
- "ā": 192,
221
- "9": 28,
222
- "ħ": 230,
223
- "tysiÄħc": 304,
224
  "sto": 309,
225
- "č": 204,
226
- "Ĕ": 211,
227
- "rz": 280,
228
- "Ę": 215,
229
- "dziesiÄħ": 272,
230
- "dziesiÄħt": 273,
231
- "dzieÅĽci": 292,
232
- "ċ": 202,
233
- "ó": 178,
234
- "siedemnaÅĽcie": 340,
235
- "ı": 240,
236
- "ede": 305,
237
- "/": 18,
238
- "osiemnaÅĽcie": 337,
239
- "µ": 116,
240
- "¤": 100,
241
- "ė": 214,
242
- "=": 4,
243
- "st": 281,
244
- "u": 87,
245
  "Ù": 152,
246
- "6": 25,
247
- "÷": 182,
248
- "ŀ": 255,
249
- "w": 89,
250
  "ò": 177,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
251
  "trzynaÅĽcie": 339,
252
- "É": 136,
253
- "Ĉ": 199,
254
- "3": 22,
255
  "ć": 198,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
256
  "iÄĻÄĩ": 269,
257
- "Ā": 191,
258
- "Æ": 133,
259
- "į": 238,
260
- "siÄħ": 266,
261
- "-": 16,
262
- "dziew": 285,
263
- "è": 167,
264
- "]": 63,
265
- "ģ": 226,
 
266
  "ľ": 253,
267
- "õ": 180,
268
- "æ": 165,
269
- "ĉ": 200,
270
- "í": 172,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
271
  "Û": 154,
272
- "à": 159,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
273
  "zer": 344,
274
- "ö": 181,
275
- "¬": 108,
276
- "W": 57,
277
- "Ą": 195,
278
- "naÅĽcie": 328,
279
- "dzieÅĽcia": 315,
280
- "{": 93,
281
- "dziesiÄĻÄĩ": 343,
282
- "piÄĻtnaÅĽcie": 331,
283
- "Ĝ": 219,
284
- "½": 124,
285
- "Ģ": 225,
286
- "Ø": 151,
287
- "Ĵ": 243,
288
- "ë": 170,
289
- "!": 5,
290
- "A": 35,
291
  "dziewiÄĻÄĩdziesiÄħt": 321,
292
- "ñ": 176,
293
- "y": 91,
294
- "Äĩ": 263,
 
 
 
 
295
  "Ò": 145,
 
 
 
 
 
 
 
 
 
 
 
 
296
  "Ü": 155,
297
- "M": 47,
298
- "siedemset": 316,
299
- "ğ": 222,
300
- "trzydzieÅĽci": 313,
301
- "i": 75,
302
- "§": 103,
303
- "®": 109,
 
 
 
 
 
304
  "Q": 51,
305
- "<pad>": 2,
306
- "|": 94,
307
- "g": 73,
308
- ":": 29,
309
- "%": 9,
310
- "Í": 140,
311
- "sta": 299,
312
- "D": 38,
313
- "iÄĻtnaÅĽcie": 330,
314
- "dz": 261,
315
- "´": 115,
316
- "B": 36,
317
- "ý": 188,
318
- "Á": 128,
319
- "dw": 278,
320
- "iÄ": 260,
321
- "Ļ": 250,
322
- "czternaÅĽcie": 336,
323
- ";": 30,
324
- "ß": 158,
325
- "Ľ": 252,
326
- "ī": 234,
327
- "^": 64,
328
- "#": 7,
329
- "Ğ": 221,
330
  "t": 86,
331
- "siede": 287,
332
- "s": 85,
333
- "O": 49,
334
- "tnaÅĽcie": 329,
335
- "³": 114,
336
- "Ė": 213,
337
- "Â": 129,
338
- "ķ": 246,
339
- "ij": 242,
340
  "szeÅĽÄĩ": 297,
341
- "piÄĻÄĩdziesiÄħt": 319,
342
- "Ě": 217,
343
- "ì": 171,
344
- "m": 79,
345
- "ÅĽcie": 300,
346
- "2": 21,
347
- "aÅĽcie": 327
 
 
348
  }
 
1
  {
2
+ "Ļ": 250,
3
+ "siedemdziesiÄħt": 317,
4
+ "set": 271,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "jede": 306,
6
+ "ĉ": 200,
7
+ "Ć": 197,
8
+ "Äĩ": 263,
9
+ "è": 167,
10
+ "5": 23,
11
+ "Þ": 157,
12
+ "Ï": 142,
13
+ "piÄĻtnaÅĽcie": 331,
14
+ "siÄħc": 303,
15
+ "cztery": 301,
16
+ "¸": 119,
17
+ "ċ": 202,
18
+ "czterysta": 325,
19
+ "Ú": 153,
20
+ "´": 115,
21
+ "İ": 239,
22
+ "ie": 259,
23
+ "ķ": 246,
24
+ "ġ": 224,
25
+ "jedenaÅĽcie": 342,
26
  "szeÅĽÄĩdziesiÄħt": 323,
27
+ "·": 118,
28
+ "@": 34,
29
+ "ù": 184,
30
+ "M": 47,
31
+ "í": 172,
32
+ "ë": 170,
33
+ "0": 18,
34
+ "Ŀ": 254,
35
+ "]": 63,
 
 
36
  "ô": 179,
37
+ "dwieÅĽcie": 308,
38
+ "=": 31,
39
+ "¬": 108,
40
+ "osiemnaÅĽcie": 337,
41
+ "dziewiÄĻÄĩ": 296,
42
+ "ĺ": 249,
43
+ "Ô": 147,
44
+ "piÄĻÄĩset": 318,
45
+ "A": 35,
46
+ "Ľ": 252,
47
+ "ÅĽc": 274,
48
+ "ø": 183,
49
  "L": 46,
50
+ "osie": 279,
51
+ "siÄħ": 266,
 
52
  "Ê": 137,
53
+ "I": 43,
54
+ "ĻÄĩ": 333,
55
+ "Ĕ": 211,
56
+ "*": 12,
57
+ "r": 84,
58
+ "Ó": 146,
59
+ "iÄĻ": 268,
60
+ "N": 48,
61
+ "siÄ": 265,
62
+ "ß": 158,
63
+ "ĭ": 236,
64
+ "8": 26,
65
+ "&": 8,
66
+ "Ç": 134,
67
+ "n": 80,
68
+ "iÄ": 260,
69
+ "6": 24,
70
+ "dziesiÄĻÄĩ": 343,
71
+ "tnaÅĽcie": 329,
72
+ "e": 71,
73
+ "û": 186,
74
+ "Ķ": 245,
75
+ "«": 107,
76
  "Õ": 148,
77
+ "dziewiÄĻÄĩset": 320,
78
+ "Z": 60,
79
+ "<": 30,
80
+ "trz": 284,
81
+ "G": 41,
82
+ "s": 85,
83
+ "B": 36,
84
  "osiemset": 311,
 
 
 
 
 
 
85
  "Ì": 139,
86
+ "P": 50,
87
+ "î": 173,
88
+ "°": 111,
89
+ "ê": 169,
90
+ "½": 124,
91
+ "+": 13,
92
+ "ede": 305,
93
+ "IJ": 241,
 
 
 
 
94
  "F": 40,
95
+ "1": 19,
96
+ "ă": 194,
97
+ "siedemnaÅĽcie": 340,
98
+ "dziesiÄħt": 273,
99
+ "trzysta": 314,
100
+ "Ę": 215,
 
 
 
 
 
 
101
  "ĸ": 247,
102
+ "Ĵ": 243,
103
+ "¨": 104,
104
+ "}": 95,
105
+ "ı": 240,
106
+ "Ħ": 229,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  "á": 160,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
108
  "Ġ": 223,
109
+ "³": 114,
110
+ "dwanaÅĽcie": 341,
111
+ "ÅĽcie": 300,
112
+ "à": 159,
113
+ "o": 81,
114
+ "À": 127,
115
+ "ý": 188,
116
+ "ī": 234,
117
+ "szesnaÅĽcie": 338,
118
+ "j": 76,
119
+ "É": 136,
120
+ "ü": 187,
121
+ "trzydzieÅĽci": 313,
122
+ "ö": 181,
123
+ "Ł": 256,
124
+ "Ĺ": 248,
125
+ "w": 89,
126
+ "cz": 277,
127
+ "ter": 283,
128
+ "R": 52,
129
+ "piÄĻÄĩdziesiÄħt": 319,
130
+ "õ": 180,
131
+ "ÿ": 190,
132
+ ",": 14,
133
+ "W": 57,
134
  "?": 33,
135
+ "ļ": 251,
136
+ "<pad>": 2,
137
+ "siedemset": 316,
138
+ "Ģ": 225,
139
+ "tysiÄħc": 304,
140
+ "[": 61,
141
+ "â": 161,
142
  "ð": 175,
143
+ "sie": 267,
144
+ "czternaÅĽcie": 336,
145
+ "X": 58,
146
+ "÷": 182,
147
+ "D": 38,
148
+ "~": 96,
149
+ "Ĥ": 227,
150
+ "Ĭ": 235,
151
+ "3": 21,
152
+ "piÄĻÄĩ": 294,
153
+ "Y": 59,
154
+ "ì": 171,
155
+ "dziewiÄĻtnaÅĽcie": 335,
156
+ "st": 281,
157
+ "į": 238,
158
+ "dziesiÄħ": 272,
159
+ "å": 164,
160
+ "er": 276,
161
  "sz": 282,
162
+ "dziew": 285,
163
+ "¡": 97,
164
+ "Í": 140,
165
+ ";": 29,
166
+ "º": 121,
167
+ "sta": 299,
168
+ "'": 9,
169
+ "Ā": 191,
170
+ ">": 32,
171
+ "Ý": 156,
172
+ "Đ": 207,
173
+ "sze": 290,
174
+ "ÅĽ": 264,
175
+ "é": 168,
176
+ "ą": 196,
 
 
 
 
 
 
177
  "¿": 126,
178
+ "czterdzieÅĽci": 310,
179
+ "Ñ": 144,
 
 
 
 
 
 
 
 
 
 
180
  "sto": 309,
181
+ "Ī": 233,
182
+ "Ċ": 201,
183
+ ")": 11,
184
+ "ÅĽÄĩ": 295,
185
+ "Ĝ": 219,
186
+ "zero": 345,
187
+ "4": 22,
188
+ "U": 55,
189
+ "×": 150,
190
+ "Ă": 193,
191
+ "J": 44,
 
 
 
 
 
 
 
 
 
192
  "Ù": 152,
193
+ "È": 135,
 
 
 
194
  "ò": 177,
195
+ "%": 7,
196
+ "/": 17,
197
+ "ty": 302,
198
+ "Á": 128,
199
+ "µ": 116,
200
+ "¦": 102,
201
+ "rz": 280,
202
+ "Ë": 138,
203
+ "p": 82,
204
+ "ĩ": 232,
205
+ "¯": 110,
206
+ "¤": 100,
207
+ "dzieÅĽcia": 315,
208
+ "Ä": 131,
209
+ "snaÅĽcie": 332,
210
+ "Ö": 149,
211
+ "et": 270,
212
+ "ě": 218,
213
+ "O": 49,
214
+ "C": 37,
215
+ "Ą": 195,
216
+ "trzy": 291,
217
+ "9": 27,
218
  "trzynaÅĽcie": 339,
 
 
 
219
  "ć": 198,
220
+ "czter": 288,
221
+ "osiem": 289,
222
+ "dzieÅĽc": 286,
223
+ "Ě": 217,
224
+ "g": 73,
225
+ "K": 45,
226
+ "dwa": 298,
227
+ "b": 68,
228
+ "ieÅĽcie": 307,
229
+ "dzie": 262,
230
+ "h": 74,
231
+ "ā": 192,
232
+ "£": 99,
233
+ "Į": 237,
234
+ "<s>": 0,
235
+ "Ė": 213,
236
+ "Ń": 258,
237
+ "a": 67,
238
+ "-": 15,
239
+ "l": 78,
240
+ "ñ": 176,
241
+ "Č": 203,
242
+ "ę": 216,
243
+ "Ď": 205,
244
  "iÄĻÄĩ": 269,
245
+ "Ē": 209,
246
+ "ij": 242,
247
+ "v": 88,
248
+ "ħ": 230,
249
+ "Ã": 130,
250
+ "ç": 166,
251
+ "ŀ": 255,
252
+ "2": 20,
253
+ "{": 93,
254
+ "$": 6,
255
  "ľ": 253,
256
+ "jeden": 326,
257
+ "ï": 174,
258
+ "ĵ": 244,
259
+ "Â": 129,
260
+ "z": 92,
261
+ "®": 109,
262
+ "Ð": 143,
263
+ "u": 87,
264
+ "Å": 132,
265
+ "f": 72,
266
+ "k": 77,
267
+ "ã": 162,
268
+ "osiemdziesiÄħt": 312,
269
+ "!": 3,
270
+ "ĕ": 212,
271
+ "y": 91,
272
+ "ğ": 222,
273
+ "¹": 120,
274
+ "siedem": 293,
275
  "Û": 154,
276
+ "dziesiÄ": 334,
277
+ "dz": 261,
278
+ "ł": 257,
279
+ "¾": 125,
280
+ "©": 105,
281
+ "Ğ": 221,
282
+ "T": 54,
283
+ "dw": 278,
284
+ "`": 66,
285
+ "đ": 208,
286
+ "Î": 141,
287
+ "ª": 106,
288
+ "ĝ": 220,
289
+ "č": 204,
290
+ "ú": 185,
291
+ "^": 64,
292
+ "i": 75,
293
+ "7": 25,
294
+ "¼": 123,
295
+ "S": 53,
296
  "zer": 344,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
297
  "dziewiÄĻÄĩdziesiÄħt": 321,
298
+ "Æ": 133,
299
+ "²": 113,
300
+ "¥": 101,
301
+ "ä": 163,
302
+ ":": 28,
303
+ "</s>": 1,
304
+ "æ": 165,
305
  "Ò": 145,
306
+ "naÅĽcie": 328,
307
+ "aÅĽcie": 327,
308
+ "m": 79,
309
+ "E": 39,
310
+ "Ĉ": 199,
311
+ "¢": 98,
312
+ "±": 112,
313
+ "ď": 206,
314
+ "c": 69,
315
+ "H": 42,
316
+ "ē": 210,
317
+ "»": 122,
318
  "Ü": 155,
319
+ "þ": 189,
320
+ "x": 90,
321
+ ".": 16,
322
+ "": 117,
323
+ "dwadzieÅĽcia": 324,
324
+ "_": 65,
325
+ "Ĩ": 231,
326
+ "ė": 214,
327
+ "ĥ": 228,
328
+ "de": 275,
329
+ "(": 10,
330
+ "dzieÅĽci": 292,
331
  "Q": 51,
332
+ "d": 70,
333
+ "szeÅĽÄĩset": 322,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
334
  "t": 86,
335
+ "ó": 178,
336
+ "|": 94,
337
+ "ģ": 226,
 
 
 
 
 
 
338
  "szeÅĽÄĩ": 297,
339
+ "siede": 287,
340
+ "\"": 4,
341
+ "§": 103,
342
+ "\\": 62,
343
+ "q": 83,
344
+ "Ø": 151,
345
+ "#": 5,
346
+ "iÄĻtnaÅĽcie": 330,
347
+ "V": 56
348
  }