m.utrobin commited on
Commit
21f6b53
·
1 Parent(s): dcc7b71

tokenizer upload

Browse files
Files changed (5) hide show
  1. added_tokens.json +169 -0
  2. merges.txt +1 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer_config.json +1382 -0
  5. vocab.json +6 -0
added_tokens.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ " ": 104,
3
+ "'": 79,
4
+ "+": 60,
5
+ "+a": 29,
6
+ "+e": 28,
7
+ "+i": 10,
8
+ "+j": 11,
9
+ "+o": 21,
10
+ "+u": 9,
11
+ "+ɨ": 26,
12
+ ".": 148,
13
+ "a": 132,
14
+ "b": 63,
15
+ "bʲ": 4,
16
+ "c": 98,
17
+ "d": 39,
18
+ "dʲ": 32,
19
+ "d͡ʒ": 24,
20
+ "e": 94,
21
+ "f": 136,
22
+ "fʲ": 15,
23
+ "g": 131,
24
+ "h": 159,
25
+ "i": 112,
26
+ "j": 170,
27
+ "k": 168,
28
+ "kʲ": 8,
29
+ "l": 138,
30
+ "lʲ": 25,
31
+ "m": 97,
32
+ "mʲ": 20,
33
+ "n": 110,
34
+ "nʲ": 18,
35
+ "o": 34,
36
+ "p": 108,
37
+ "pʲ": 14,
38
+ "q": 103,
39
+ "r": 141,
40
+ "rʲ": 23,
41
+ "s": 144,
42
+ "sʲ": 6,
43
+ "t": 84,
44
+ "tʲ": 16,
45
+ "t͡": 13,
46
+ "t͡s": 17,
47
+ "t͡ɕ": 22,
48
+ "t͡ʃ": 27,
49
+ "u": 70,
50
+ "v": 101,
51
+ "vʲ": 19,
52
+ "w": 96,
53
+ "x": 58,
54
+ "xʲ": 30,
55
+ "y": 56,
56
+ "z": 95,
57
+ "zʲ": 5,
58
+ "æ": 67,
59
+ "ç": 129,
60
+ "ð": 162,
61
+ "ø": 54,
62
+ "ħ": 61,
63
+ "ŋ": 35,
64
+ "œ": 143,
65
+ "ǀ": 125,
66
+ "ǁ": 68,
67
+ "ǂ": 166,
68
+ "ǃ": 89,
69
+ "ɐ": 107,
70
+ "ɑ": 137,
71
+ "ɒ": 164,
72
+ "ɓ": 169,
73
+ "ɔ": 57,
74
+ "ɕ": 49,
75
+ "ɕʲ": 31,
76
+ "ɖ": 145,
77
+ "ɗ": 154,
78
+ "ɘ": 158,
79
+ "ə": 45,
80
+ "ɚ": 72,
81
+ "ɛ": 109,
82
+ "ɜ": 62,
83
+ "ɝ": 92,
84
+ "ɞ": 46,
85
+ "ɟ": 65,
86
+ "ɠ": 50,
87
+ "ɡ": 33,
88
+ "ɢ": 126,
89
+ "ɣ": 122,
90
+ "ɤ": 119,
91
+ "ɥ": 99,
92
+ "ɦ": 117,
93
+ "ɧ": 77,
94
+ "ɨ": 76,
95
+ "ɪ": 42,
96
+ "ɫ": 87,
97
+ "ɬ": 71,
98
+ "ɭ": 142,
99
+ "ɮ": 74,
100
+ "ɯ": 140,
101
+ "ɰ": 149,
102
+ "ɱ": 128,
103
+ "ɲ": 81,
104
+ "ɳ": 85,
105
+ "ɴ": 102,
106
+ "ɵ": 44,
107
+ "ɶ": 59,
108
+ "ɸ": 115,
109
+ "ɹ": 78,
110
+ "ɺ": 130,
111
+ "ɻ": 123,
112
+ "ɽ": 160,
113
+ "ɾ": 157,
114
+ "ʀ": 88,
115
+ "ʁ": 93,
116
+ "ʂ": 55,
117
+ "ʂʲ": 7,
118
+ "ʃ": 153,
119
+ "ʄ": 165,
120
+ "ʈ": 156,
121
+ "ʈ͡ʂ": 12,
122
+ "ʉ": 80,
123
+ "ʊ": 139,
124
+ "ʋ": 161,
125
+ "ʌ": 40,
126
+ "ʍ": 83,
127
+ "ʎ": 106,
128
+ "ʏ": 86,
129
+ "ʐ": 120,
130
+ "ʑ": 66,
131
+ "ʒ": 36,
132
+ "ʔ": 135,
133
+ "ʕ": 75,
134
+ "ʘ": 113,
135
+ "ʙ": 111,
136
+ "ʛ": 51,
137
+ "ʜ": 127,
138
+ "ʝ": 100,
139
+ "ʟ": 114,
140
+ "ʡ": 38,
141
+ "ʢ": 105,
142
+ "ʤ": 152,
143
+ "ʧ": 146,
144
+ "ʰ": 64,
145
+ "ʱ": 121,
146
+ "ʲ": 150,
147
+ "ʴ": 155,
148
+ "ʷ": 69,
149
+ "ʼ": 151,
150
+ "ˈ": 52,
151
+ "ˌ": 90,
152
+ "ː": 118,
153
+ "ˑ": 134,
154
+ "˞": 91,
155
+ "ˠ": 147,
156
+ "ˤ": 41,
157
+ "̩": 48,
158
+ "͡": 116,
159
+ "β": 43,
160
+ "θ": 37,
161
+ "χ": 82,
162
+ "ᵻ": 124,
163
+ "↑": 167,
164
+ "→": 53,
165
+ "↓": 133,
166
+ "↗": 47,
167
+ "↘": 73,
168
+ "ⱱ": 163
169
+ }
merges.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ #version: 0.2
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|bos|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eos|>",
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 +1,1382 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|pad|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|unk|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|bos|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<|eos|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "bʲ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "5": {
45
+ "content": "zʲ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "6": {
53
+ "content": "sʲ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "7": {
61
+ "content": "ʂʲ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "8": {
69
+ "content": "kʲ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "9": {
77
+ "content": "+u",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "10": {
85
+ "content": "+i",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "11": {
93
+ "content": "+j",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "12": {
101
+ "content": "ʈ͡ʂ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "13": {
109
+ "content": "t͡",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "14": {
117
+ "content": "pʲ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "15": {
125
+ "content": "fʲ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "16": {
133
+ "content": "tʲ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "17": {
141
+ "content": "t͡s",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "18": {
149
+ "content": "nʲ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "19": {
157
+ "content": "vʲ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "20": {
165
+ "content": "mʲ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "21": {
173
+ "content": "+o",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "22": {
181
+ "content": "t͡ɕ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "23": {
189
+ "content": "rʲ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "24": {
197
+ "content": "d͡ʒ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "25": {
205
+ "content": "lʲ",
206
+ "lstrip": false,
207
+ "normalized": true,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "26": {
213
+ "content": "+ɨ",
214
+ "lstrip": false,
215
+ "normalized": true,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": false
219
+ },
220
+ "27": {
221
+ "content": "t͡ʃ",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": false
227
+ },
228
+ "28": {
229
+ "content": "+e",
230
+ "lstrip": false,
231
+ "normalized": true,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": false
235
+ },
236
+ "29": {
237
+ "content": "+a",
238
+ "lstrip": false,
239
+ "normalized": true,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": false
243
+ },
244
+ "30": {
245
+ "content": "xʲ",
246
+ "lstrip": false,
247
+ "normalized": true,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": false
251
+ },
252
+ "31": {
253
+ "content": "ɕʲ",
254
+ "lstrip": false,
255
+ "normalized": true,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": false
259
+ },
260
+ "32": {
261
+ "content": "dʲ",
262
+ "lstrip": false,
263
+ "normalized": true,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": false
267
+ },
268
+ "33": {
269
+ "content": "ɡ",
270
+ "lstrip": false,
271
+ "normalized": true,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": false
275
+ },
276
+ "34": {
277
+ "content": "o",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": false
283
+ },
284
+ "35": {
285
+ "content": "ŋ",
286
+ "lstrip": false,
287
+ "normalized": true,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": false
291
+ },
292
+ "36": {
293
+ "content": "ʒ",
294
+ "lstrip": false,
295
+ "normalized": true,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": false
299
+ },
300
+ "37": {
301
+ "content": "θ",
302
+ "lstrip": false,
303
+ "normalized": true,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": false
307
+ },
308
+ "38": {
309
+ "content": "ʡ",
310
+ "lstrip": false,
311
+ "normalized": true,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": false
315
+ },
316
+ "39": {
317
+ "content": "d",
318
+ "lstrip": false,
319
+ "normalized": true,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": false
323
+ },
324
+ "40": {
325
+ "content": "ʌ",
326
+ "lstrip": false,
327
+ "normalized": true,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": false
331
+ },
332
+ "41": {
333
+ "content": "ˤ",
334
+ "lstrip": false,
335
+ "normalized": true,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": false
339
+ },
340
+ "42": {
341
+ "content": "ɪ",
342
+ "lstrip": false,
343
+ "normalized": true,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": false
347
+ },
348
+ "43": {
349
+ "content": "β",
350
+ "lstrip": false,
351
+ "normalized": true,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": false
355
+ },
356
+ "44": {
357
+ "content": "ɵ",
358
+ "lstrip": false,
359
+ "normalized": true,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": false
363
+ },
364
+ "45": {
365
+ "content": "ə",
366
+ "lstrip": false,
367
+ "normalized": true,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": false
371
+ },
372
+ "46": {
373
+ "content": "ɞ",
374
+ "lstrip": false,
375
+ "normalized": true,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": false
379
+ },
380
+ "47": {
381
+ "content": "↗",
382
+ "lstrip": false,
383
+ "normalized": true,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": false
387
+ },
388
+ "48": {
389
+ "content": "̩",
390
+ "lstrip": false,
391
+ "normalized": true,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": false
395
+ },
396
+ "49": {
397
+ "content": "ɕ",
398
+ "lstrip": false,
399
+ "normalized": true,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": false
403
+ },
404
+ "50": {
405
+ "content": "ɠ",
406
+ "lstrip": false,
407
+ "normalized": true,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": false
411
+ },
412
+ "51": {
413
+ "content": "ʛ",
414
+ "lstrip": false,
415
+ "normalized": true,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": false
419
+ },
420
+ "52": {
421
+ "content": "ˈ",
422
+ "lstrip": false,
423
+ "normalized": true,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": false
427
+ },
428
+ "53": {
429
+ "content": "→",
430
+ "lstrip": false,
431
+ "normalized": true,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": false
435
+ },
436
+ "54": {
437
+ "content": "ø",
438
+ "lstrip": false,
439
+ "normalized": true,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": false
443
+ },
444
+ "55": {
445
+ "content": "ʂ",
446
+ "lstrip": false,
447
+ "normalized": true,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": false
451
+ },
452
+ "56": {
453
+ "content": "y",
454
+ "lstrip": false,
455
+ "normalized": true,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": false
459
+ },
460
+ "57": {
461
+ "content": "ɔ",
462
+ "lstrip": false,
463
+ "normalized": true,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": false
467
+ },
468
+ "58": {
469
+ "content": "x",
470
+ "lstrip": false,
471
+ "normalized": true,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": false
475
+ },
476
+ "59": {
477
+ "content": "ɶ",
478
+ "lstrip": false,
479
+ "normalized": true,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": false
483
+ },
484
+ "60": {
485
+ "content": "+",
486
+ "lstrip": false,
487
+ "normalized": true,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": false
491
+ },
492
+ "61": {
493
+ "content": "ħ",
494
+ "lstrip": false,
495
+ "normalized": true,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": false
499
+ },
500
+ "62": {
501
+ "content": "ɜ",
502
+ "lstrip": false,
503
+ "normalized": true,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": false
507
+ },
508
+ "63": {
509
+ "content": "b",
510
+ "lstrip": false,
511
+ "normalized": true,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": false
515
+ },
516
+ "64": {
517
+ "content": "ʰ",
518
+ "lstrip": false,
519
+ "normalized": true,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": false
523
+ },
524
+ "65": {
525
+ "content": "ɟ",
526
+ "lstrip": false,
527
+ "normalized": true,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": false
531
+ },
532
+ "66": {
533
+ "content": "ʑ",
534
+ "lstrip": false,
535
+ "normalized": true,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": false
539
+ },
540
+ "67": {
541
+ "content": "æ",
542
+ "lstrip": false,
543
+ "normalized": true,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": false
547
+ },
548
+ "68": {
549
+ "content": "ǁ",
550
+ "lstrip": false,
551
+ "normalized": true,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": false
555
+ },
556
+ "69": {
557
+ "content": "ʷ",
558
+ "lstrip": false,
559
+ "normalized": true,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": false
563
+ },
564
+ "70": {
565
+ "content": "u",
566
+ "lstrip": false,
567
+ "normalized": true,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": false
571
+ },
572
+ "71": {
573
+ "content": "ɬ",
574
+ "lstrip": false,
575
+ "normalized": true,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": false
579
+ },
580
+ "72": {
581
+ "content": "ɚ",
582
+ "lstrip": false,
583
+ "normalized": true,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": false
587
+ },
588
+ "73": {
589
+ "content": "↘",
590
+ "lstrip": false,
591
+ "normalized": true,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": false
595
+ },
596
+ "74": {
597
+ "content": "ɮ",
598
+ "lstrip": false,
599
+ "normalized": true,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": false
603
+ },
604
+ "75": {
605
+ "content": "ʕ",
606
+ "lstrip": false,
607
+ "normalized": true,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": false
611
+ },
612
+ "76": {
613
+ "content": "ɨ",
614
+ "lstrip": false,
615
+ "normalized": true,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": false
619
+ },
620
+ "77": {
621
+ "content": "ɧ",
622
+ "lstrip": false,
623
+ "normalized": true,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": false
627
+ },
628
+ "78": {
629
+ "content": "ɹ",
630
+ "lstrip": false,
631
+ "normalized": true,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": false
635
+ },
636
+ "79": {
637
+ "content": "'",
638
+ "lstrip": false,
639
+ "normalized": true,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": false
643
+ },
644
+ "80": {
645
+ "content": "ʉ",
646
+ "lstrip": false,
647
+ "normalized": true,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": false
651
+ },
652
+ "81": {
653
+ "content": "ɲ",
654
+ "lstrip": false,
655
+ "normalized": true,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": false
659
+ },
660
+ "82": {
661
+ "content": "χ",
662
+ "lstrip": false,
663
+ "normalized": true,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": false
667
+ },
668
+ "83": {
669
+ "content": "ʍ",
670
+ "lstrip": false,
671
+ "normalized": true,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": false
675
+ },
676
+ "84": {
677
+ "content": "t",
678
+ "lstrip": false,
679
+ "normalized": true,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": false
683
+ },
684
+ "85": {
685
+ "content": "ɳ",
686
+ "lstrip": false,
687
+ "normalized": true,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": false
691
+ },
692
+ "86": {
693
+ "content": "ʏ",
694
+ "lstrip": false,
695
+ "normalized": true,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": false
699
+ },
700
+ "87": {
701
+ "content": "ɫ",
702
+ "lstrip": false,
703
+ "normalized": true,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": false
707
+ },
708
+ "88": {
709
+ "content": "ʀ",
710
+ "lstrip": false,
711
+ "normalized": true,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": false
715
+ },
716
+ "89": {
717
+ "content": "ǃ",
718
+ "lstrip": false,
719
+ "normalized": true,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": false
723
+ },
724
+ "90": {
725
+ "content": "ˌ",
726
+ "lstrip": false,
727
+ "normalized": true,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": false
731
+ },
732
+ "91": {
733
+ "content": "˞",
734
+ "lstrip": false,
735
+ "normalized": true,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": false
739
+ },
740
+ "92": {
741
+ "content": "ɝ",
742
+ "lstrip": false,
743
+ "normalized": true,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": false
747
+ },
748
+ "93": {
749
+ "content": "ʁ",
750
+ "lstrip": false,
751
+ "normalized": true,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": false
755
+ },
756
+ "94": {
757
+ "content": "e",
758
+ "lstrip": false,
759
+ "normalized": true,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": false
763
+ },
764
+ "95": {
765
+ "content": "z",
766
+ "lstrip": false,
767
+ "normalized": true,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": false
771
+ },
772
+ "96": {
773
+ "content": "w",
774
+ "lstrip": false,
775
+ "normalized": true,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": false
779
+ },
780
+ "97": {
781
+ "content": "m",
782
+ "lstrip": false,
783
+ "normalized": true,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": false
787
+ },
788
+ "98": {
789
+ "content": "c",
790
+ "lstrip": false,
791
+ "normalized": true,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": false
795
+ },
796
+ "99": {
797
+ "content": "ɥ",
798
+ "lstrip": false,
799
+ "normalized": true,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": false
803
+ },
804
+ "100": {
805
+ "content": "ʝ",
806
+ "lstrip": false,
807
+ "normalized": true,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": false
811
+ },
812
+ "101": {
813
+ "content": "v",
814
+ "lstrip": false,
815
+ "normalized": true,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": false
819
+ },
820
+ "102": {
821
+ "content": "ɴ",
822
+ "lstrip": false,
823
+ "normalized": true,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": false
827
+ },
828
+ "103": {
829
+ "content": "q",
830
+ "lstrip": false,
831
+ "normalized": true,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": false
835
+ },
836
+ "104": {
837
+ "content": " ",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "105": {
845
+ "content": "ʢ",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ },
852
+ "106": {
853
+ "content": "ʎ",
854
+ "lstrip": false,
855
+ "normalized": true,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": false
859
+ },
860
+ "107": {
861
+ "content": "ɐ",
862
+ "lstrip": false,
863
+ "normalized": true,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": false
867
+ },
868
+ "108": {
869
+ "content": "p",
870
+ "lstrip": false,
871
+ "normalized": true,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": false
875
+ },
876
+ "109": {
877
+ "content": "ɛ",
878
+ "lstrip": false,
879
+ "normalized": true,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": false
883
+ },
884
+ "110": {
885
+ "content": "n",
886
+ "lstrip": false,
887
+ "normalized": true,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": false
891
+ },
892
+ "111": {
893
+ "content": "ʙ",
894
+ "lstrip": false,
895
+ "normalized": true,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": false
899
+ },
900
+ "112": {
901
+ "content": "i",
902
+ "lstrip": false,
903
+ "normalized": true,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": false
907
+ },
908
+ "113": {
909
+ "content": "ʘ",
910
+ "lstrip": false,
911
+ "normalized": true,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": false
915
+ },
916
+ "114": {
917
+ "content": "ʟ",
918
+ "lstrip": false,
919
+ "normalized": true,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": false
923
+ },
924
+ "115": {
925
+ "content": "ɸ",
926
+ "lstrip": false,
927
+ "normalized": true,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": false
931
+ },
932
+ "116": {
933
+ "content": "͡",
934
+ "lstrip": false,
935
+ "normalized": true,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": false
939
+ },
940
+ "117": {
941
+ "content": "ɦ",
942
+ "lstrip": false,
943
+ "normalized": true,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": false
947
+ },
948
+ "118": {
949
+ "content": "ː",
950
+ "lstrip": false,
951
+ "normalized": true,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": false
955
+ },
956
+ "119": {
957
+ "content": "ɤ",
958
+ "lstrip": false,
959
+ "normalized": true,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": false
963
+ },
964
+ "120": {
965
+ "content": "ʐ",
966
+ "lstrip": false,
967
+ "normalized": true,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": false
971
+ },
972
+ "121": {
973
+ "content": "ʱ",
974
+ "lstrip": false,
975
+ "normalized": true,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": false
979
+ },
980
+ "122": {
981
+ "content": "ɣ",
982
+ "lstrip": false,
983
+ "normalized": true,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": false
987
+ },
988
+ "123": {
989
+ "content": "ɻ",
990
+ "lstrip": false,
991
+ "normalized": true,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": false
995
+ },
996
+ "124": {
997
+ "content": "ᵻ",
998
+ "lstrip": false,
999
+ "normalized": true,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": false
1003
+ },
1004
+ "125": {
1005
+ "content": "ǀ",
1006
+ "lstrip": false,
1007
+ "normalized": true,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": false
1011
+ },
1012
+ "126": {
1013
+ "content": "ɢ",
1014
+ "lstrip": false,
1015
+ "normalized": true,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": false
1019
+ },
1020
+ "127": {
1021
+ "content": "ʜ",
1022
+ "lstrip": false,
1023
+ "normalized": true,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": false
1027
+ },
1028
+ "128": {
1029
+ "content": "ɱ",
1030
+ "lstrip": false,
1031
+ "normalized": true,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": false
1035
+ },
1036
+ "129": {
1037
+ "content": "ç",
1038
+ "lstrip": false,
1039
+ "normalized": true,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": false
1043
+ },
1044
+ "130": {
1045
+ "content": "ɺ",
1046
+ "lstrip": false,
1047
+ "normalized": true,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": false
1051
+ },
1052
+ "131": {
1053
+ "content": "g",
1054
+ "lstrip": false,
1055
+ "normalized": true,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": false
1059
+ },
1060
+ "132": {
1061
+ "content": "a",
1062
+ "lstrip": false,
1063
+ "normalized": true,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": false
1067
+ },
1068
+ "133": {
1069
+ "content": "↓",
1070
+ "lstrip": false,
1071
+ "normalized": true,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": false
1075
+ },
1076
+ "134": {
1077
+ "content": "ˑ",
1078
+ "lstrip": false,
1079
+ "normalized": true,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": false
1083
+ },
1084
+ "135": {
1085
+ "content": "ʔ",
1086
+ "lstrip": false,
1087
+ "normalized": true,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": false
1091
+ },
1092
+ "136": {
1093
+ "content": "f",
1094
+ "lstrip": false,
1095
+ "normalized": true,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": false
1099
+ },
1100
+ "137": {
1101
+ "content": "ɑ",
1102
+ "lstrip": false,
1103
+ "normalized": true,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": false
1107
+ },
1108
+ "138": {
1109
+ "content": "l",
1110
+ "lstrip": false,
1111
+ "normalized": true,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": false
1115
+ },
1116
+ "139": {
1117
+ "content": "ʊ",
1118
+ "lstrip": false,
1119
+ "normalized": true,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": false
1123
+ },
1124
+ "140": {
1125
+ "content": "ɯ",
1126
+ "lstrip": false,
1127
+ "normalized": true,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": false
1131
+ },
1132
+ "141": {
1133
+ "content": "r",
1134
+ "lstrip": false,
1135
+ "normalized": true,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": false
1139
+ },
1140
+ "142": {
1141
+ "content": "ɭ",
1142
+ "lstrip": false,
1143
+ "normalized": true,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": false
1147
+ },
1148
+ "143": {
1149
+ "content": "œ",
1150
+ "lstrip": false,
1151
+ "normalized": true,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": false
1155
+ },
1156
+ "144": {
1157
+ "content": "s",
1158
+ "lstrip": false,
1159
+ "normalized": true,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": false
1163
+ },
1164
+ "145": {
1165
+ "content": "ɖ",
1166
+ "lstrip": false,
1167
+ "normalized": true,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": false
1171
+ },
1172
+ "146": {
1173
+ "content": "ʧ",
1174
+ "lstrip": false,
1175
+ "normalized": true,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": false
1179
+ },
1180
+ "147": {
1181
+ "content": "ˠ",
1182
+ "lstrip": false,
1183
+ "normalized": true,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": false
1187
+ },
1188
+ "148": {
1189
+ "content": ".",
1190
+ "lstrip": false,
1191
+ "normalized": true,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": false
1195
+ },
1196
+ "149": {
1197
+ "content": "ɰ",
1198
+ "lstrip": false,
1199
+ "normalized": true,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": false
1203
+ },
1204
+ "150": {
1205
+ "content": "ʲ",
1206
+ "lstrip": false,
1207
+ "normalized": true,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": false
1211
+ },
1212
+ "151": {
1213
+ "content": "ʼ",
1214
+ "lstrip": false,
1215
+ "normalized": true,
1216
+ "rstrip": false,
1217
+ "single_word": false,
1218
+ "special": false
1219
+ },
1220
+ "152": {
1221
+ "content": "ʤ",
1222
+ "lstrip": false,
1223
+ "normalized": true,
1224
+ "rstrip": false,
1225
+ "single_word": false,
1226
+ "special": false
1227
+ },
1228
+ "153": {
1229
+ "content": "ʃ",
1230
+ "lstrip": false,
1231
+ "normalized": true,
1232
+ "rstrip": false,
1233
+ "single_word": false,
1234
+ "special": false
1235
+ },
1236
+ "154": {
1237
+ "content": "ɗ",
1238
+ "lstrip": false,
1239
+ "normalized": true,
1240
+ "rstrip": false,
1241
+ "single_word": false,
1242
+ "special": false
1243
+ },
1244
+ "155": {
1245
+ "content": "ʴ",
1246
+ "lstrip": false,
1247
+ "normalized": true,
1248
+ "rstrip": false,
1249
+ "single_word": false,
1250
+ "special": false
1251
+ },
1252
+ "156": {
1253
+ "content": "ʈ",
1254
+ "lstrip": false,
1255
+ "normalized": true,
1256
+ "rstrip": false,
1257
+ "single_word": false,
1258
+ "special": false
1259
+ },
1260
+ "157": {
1261
+ "content": "ɾ",
1262
+ "lstrip": false,
1263
+ "normalized": true,
1264
+ "rstrip": false,
1265
+ "single_word": false,
1266
+ "special": false
1267
+ },
1268
+ "158": {
1269
+ "content": "ɘ",
1270
+ "lstrip": false,
1271
+ "normalized": true,
1272
+ "rstrip": false,
1273
+ "single_word": false,
1274
+ "special": false
1275
+ },
1276
+ "159": {
1277
+ "content": "h",
1278
+ "lstrip": false,
1279
+ "normalized": true,
1280
+ "rstrip": false,
1281
+ "single_word": false,
1282
+ "special": false
1283
+ },
1284
+ "160": {
1285
+ "content": "ɽ",
1286
+ "lstrip": false,
1287
+ "normalized": true,
1288
+ "rstrip": false,
1289
+ "single_word": false,
1290
+ "special": false
1291
+ },
1292
+ "161": {
1293
+ "content": "ʋ",
1294
+ "lstrip": false,
1295
+ "normalized": true,
1296
+ "rstrip": false,
1297
+ "single_word": false,
1298
+ "special": false
1299
+ },
1300
+ "162": {
1301
+ "content": "ð",
1302
+ "lstrip": false,
1303
+ "normalized": true,
1304
+ "rstrip": false,
1305
+ "single_word": false,
1306
+ "special": false
1307
+ },
1308
+ "163": {
1309
+ "content": "ⱱ",
1310
+ "lstrip": false,
1311
+ "normalized": true,
1312
+ "rstrip": false,
1313
+ "single_word": false,
1314
+ "special": false
1315
+ },
1316
+ "164": {
1317
+ "content": "ɒ",
1318
+ "lstrip": false,
1319
+ "normalized": true,
1320
+ "rstrip": false,
1321
+ "single_word": false,
1322
+ "special": false
1323
+ },
1324
+ "165": {
1325
+ "content": "ʄ",
1326
+ "lstrip": false,
1327
+ "normalized": true,
1328
+ "rstrip": false,
1329
+ "single_word": false,
1330
+ "special": false
1331
+ },
1332
+ "166": {
1333
+ "content": "ǂ",
1334
+ "lstrip": false,
1335
+ "normalized": true,
1336
+ "rstrip": false,
1337
+ "single_word": false,
1338
+ "special": false
1339
+ },
1340
+ "167": {
1341
+ "content": "↑",
1342
+ "lstrip": false,
1343
+ "normalized": true,
1344
+ "rstrip": false,
1345
+ "single_word": false,
1346
+ "special": false
1347
+ },
1348
+ "168": {
1349
+ "content": "k",
1350
+ "lstrip": false,
1351
+ "normalized": true,
1352
+ "rstrip": false,
1353
+ "single_word": false,
1354
+ "special": false
1355
+ },
1356
+ "169": {
1357
+ "content": "ɓ",
1358
+ "lstrip": false,
1359
+ "normalized": true,
1360
+ "rstrip": false,
1361
+ "single_word": false,
1362
+ "special": false
1363
+ },
1364
+ "170": {
1365
+ "content": "j",
1366
+ "lstrip": false,
1367
+ "normalized": true,
1368
+ "rstrip": false,
1369
+ "single_word": false,
1370
+ "special": false
1371
+ }
1372
+ },
1373
+ "bos_token": "<|bos|>",
1374
+ "clean_up_tokenization_spaces": false,
1375
+ "eos_token": "<|eos|>",
1376
+ "errors": "replace",
1377
+ "extra_special_tokens": {},
1378
+ "model_max_length": 1000000000000000019884624838656,
1379
+ "pad_token": "<|pad|>",
1380
+ "tokenizer_class": "WhisperTokenizer",
1381
+ "unk_token": "<|unk|>"
1382
+ }
vocab.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|bos|>": 2,
3
+ "<|eos|>": 3,
4
+ "<|pad|>": 0,
5
+ "<|unk|>": 1
6
+ }