failed09/bashkir-diacritics-restorer
090
1{
2 "generated_from": "experiments/diacritics_restorer/data/train.parquet",
3 "min_count": 50,
4 "allowed": {
5 "у": [
6 "ү",
7 "ө"
8 ],
9 "э": [
10 "ә"
11 ],
12 "a": [
13 "ә"
14 ],
15 "е": [
16 "ә",
17 "ө"
18 ],
19 "e": [
20 "ә"
21 ],
22 "g": [
23 "ғ"
24 ],
25 "н": [
26 "ң"
27 ],
28 "x": [
29 "һ"
30 ],
31 "n": [
32 "ң"
33 ],
34 "H": [
35 "Һ",
36 "һ"
37 ],
38 "г": [
39 "ғ"
40 ],
41 "s": [
42 "ҫ"
43 ],
44 "q": [
45 "ҡ"
46 ],
47 "х": [
48 "һ"
49 ],
50 "к": [
51 "ҡ"
52 ],
53 "о": [
54 "ө"
55 ],
56 "с": [
57 "ҫ"
58 ],
59 "з": [
60 "ҙ"
61 ],
62 "Э": [
63 "Ә"
64 ],
65 "z": [
66 "ҙ"
67 ],
68 "o": [
69 "ө"
70 ],
71 "а": [
72 "ә"
73 ],
74 "u": [
75 "ү"
76 ],
77 "k": [
78 "ҡ"
79 ],
80 "h": [
81 "һ"
82 ],
83 "Х": [
84 "Һ"
85 ],
86 "У": [
87 "Ү",
88 "Ө"
89 ],
90 "О": [
91 "Ө"
92 ],
93 "Е": [
94 "Ә",
95 "Ө"
96 ],
97 "К": [
98 "Ҡ"
99 ],
100 "G": [
101 "Ғ"
102 ],
103 "Q": [
104 "Ҡ"
105 ],
106 "Г": [
107 "Ғ"
108 ],
109 "E": [
110 "Ә"
111 ],
112 "А": [
113 "Ә"
114 ],
115 "З": [
116 "Ҙ"
117 ],
118 "X": [
119 "Һ"
120 ],
121 "K": [
122 "Ҡ"
123 ],
124 "U": [
125 "Ү"
126 ],
127 "A": [
128 "Ә"
129 ],
130 "O": [
131 "Ө"
132 ],
133 "Н": [
134 "Ң"
135 ],
136 "С": [
137 "Ҫ"
138 ],
139 "Z": [
140 "Ҙ"
141 ],
142 "N": [
143 "Ң"
144 ],
145 "S": [
146 "Ҫ"
147 ]
148 },
149 "counts": {
150 "у": {
151 "ү": 211522,
152 "ө": 14560
153 },
154 "э": {
155 "ә": 1029251
156 },
157 "a": {
158 "ә": 49846
159 },
160 "е": {
161 "ә": 49632,
162 "ө": 14554
163 },
164 "e": {
165 "ә": 49784
166 },
167 "g": {
168 "ғ": 31057
169 },
170 "н": {
171 "ң": 182526
172 },
173 "x": {
174 "һ": 14751
175 },
176 "n": {
177 "ң": 20553
178 },
179 "H": {
180 "һ": 14758,
181 "Һ": 806
182 },
183 "г": {
184 "ғ": 272450
185 },
186 "s": {
187 "ҫ": 6237
188 },
189 "q": {
190 "ҡ": 31298
191 },
192 "х": {
193 "һ": 246360
194 },
195 "к": {
196 "ҡ": 398135
197 },
198 "о": {
199 "ө": 243152
200 },
201 "с": {
202 "ҫ": 55590
203 },
204 "з": {
205 "ҙ": 384175
206 },
207 "Э": {
208 "Ә": 18540
209 },
210 "z": {
211 "ҙ": 43099
212 },
213 "o": {
214 "ө": 14626
215 },
216 "а": {
217 "ә": 49872
218 },
219 "u": {
220 "ү": 23841
221 },
222 "k": {
223 "ҡ": 31495
224 },
225 "h": {
226 "һ": 14790
227 },
228 "Х": {
229 "Һ": 10158
230 },
231 "У": {
232 "Ү": 5624,
233 "Ө": 370
234 },
235 "О": {
236 "Ө": 6212
237 },
238 "Е": {
239 "Ә": 879,
240 "Ө": 395
241 },
242 "К": {
243 "Ҡ": 21263
244 },
245 "G": {
246 "Ғ": 762
247 },
248 "Q": {
249 "Ҡ": 1619
250 },
251 "Г": {
252 "Ғ": 6751
253 },
254 "E": {
255 "Ә": 878
256 },
257 "А": {
258 "Ә": 879
259 },
260 "З": {
261 "Ҙ": 611
262 },
263 "X": {
264 "Һ": 763
265 },
266 "K": {
267 "Ҡ": 1654
268 },
269 "U": {
270 "Ү": 625
271 },
272 "A": {
273 "Ә": 922
274 },
275 "O": {
276 "Ө": 359
277 },
278 "Н": {
279 "Ң": 101
280 },
281 "С": {
282 "Ҫ": 51
283 },
284 "Z": {
285 "Ҙ": 60
286 },
287 "N": {
288 "Ң": 20553
289 },
290 "S": {
291 "Ҫ": 6237
292 }
293 },
294 "skipped_length_mismatch": 0
295}