Upload tokenizer
Browse files- tokenizer.json +144 -144
- vocab.json +1 -1
tokenizer.json
CHANGED
@@ -106,154 +106,154 @@
|
|
106 |
"PAD": 1,
|
107 |
"WORD_BOUNDARY": 2,
|
108 |
"UTT_BOUNDARY": 3,
|
109 |
-
"
|
110 |
-
"
|
111 |
-
"
|
112 |
"k": 7,
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
116 |
-
"
|
117 |
-
"
|
118 |
-
"
|
119 |
-
"
|
120 |
-
"
|
121 |
-
"
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
150 |
-
"
|
151 |
-
"
|
152 |
-
"
|
153 |
-
"
|
154 |
-
"
|
155 |
-
"
|
156 |
-
"
|
157 |
-
"
|
158 |
-
"
|
159 |
-
"
|
160 |
-
"
|
161 |
-
"
|
162 |
-
"
|
163 |
-
"
|
164 |
-
"
|
165 |
-
"
|
166 |
-
"
|
167 |
-
"
|
168 |
-
"
|
169 |
-
"
|
170 |
-
"
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
-
"
|
175 |
-
"
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"
|
179 |
-
"
|
180 |
-
"
|
181 |
-
"
|
182 |
-
"
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
186 |
-
"
|
187 |
-
"
|
188 |
-
"
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
192 |
-
"
|
193 |
-
"
|
194 |
-
"
|
195 |
-
"
|
196 |
-
"
|
197 |
-
"
|
198 |
-
"
|
199 |
-
"
|
200 |
-
"
|
201 |
-
"
|
202 |
-
"
|
203 |
-
"
|
204 |
-
"
|
205 |
-
"
|
206 |
-
"
|
207 |
-
"
|
208 |
-
"
|
209 |
-
"
|
210 |
-
"
|
211 |
-
"
|
212 |
-
"
|
213 |
-
"
|
214 |
-
"
|
215 |
-
"
|
216 |
-
"
|
217 |
-
"
|
218 |
-
"
|
219 |
-
"
|
220 |
-
"
|
221 |
-
"
|
222 |
-
"
|
223 |
-
"
|
224 |
-
"
|
225 |
-
"
|
226 |
-
"
|
227 |
-
"
|
228 |
-
"
|
229 |
-
"
|
230 |
-
"
|
231 |
-
"
|
232 |
-
"
|
233 |
-
"
|
234 |
-
"
|
235 |
-
"
|
236 |
-
"
|
237 |
-
"
|
238 |
-
"
|
239 |
-
"
|
240 |
-
"
|
241 |
-
"
|
242 |
-
"
|
243 |
-
"
|
244 |
-
"
|
245 |
-
"
|
246 |
-
"
|
247 |
-
"
|
248 |
-
"
|
249 |
-
"
|
250 |
-
"
|
251 |
"iːŭ˩˧": 146,
|
252 |
"iːŭ˨": 147,
|
253 |
-
"
|
254 |
"uːĭ˧˩̰": 149,
|
255 |
-
"
|
256 |
-
"
|
257 |
},
|
258 |
"unk_token": "UNK"
|
259 |
}
|
|
|
106 |
"PAD": 1,
|
107 |
"WORD_BOUNDARY": 2,
|
108 |
"UTT_BOUNDARY": 3,
|
109 |
+
"j": 4,
|
110 |
+
"ɐ˥": 5,
|
111 |
+
"t": 6,
|
112 |
"k": 7,
|
113 |
+
"ɐu˧˥": 8,
|
114 |
+
"i˨": 9,
|
115 |
+
"n": 10,
|
116 |
+
"i˧˩̰": 11,
|
117 |
+
"y˨": 12,
|
118 |
+
"s": 13,
|
119 |
+
"ɐ˨": 14,
|
120 |
+
"p": 15,
|
121 |
+
"ts": 16,
|
122 |
+
"ɐu˥": 17,
|
123 |
+
"ɪ̞˧˥": 18,
|
124 |
+
"ŋ": 19,
|
125 |
+
"ɵ˧": 20,
|
126 |
+
"a̞˧": 21,
|
127 |
+
"l": 22,
|
128 |
+
"ʊ̟˥": 23,
|
129 |
+
"a̞˧˩̰": 24,
|
130 |
+
"ɛ˥": 25,
|
131 |
+
"ei˩˧": 26,
|
132 |
+
"w": 27,
|
133 |
+
"a̞˨": 28,
|
134 |
+
"ɐi˧˥": 29,
|
135 |
+
"a̞˧˥": 30,
|
136 |
+
"m̩˧˥": 31,
|
137 |
+
"m": 32,
|
138 |
+
"ou˥": 33,
|
139 |
+
"ei˥": 34,
|
140 |
+
"i˧": 35,
|
141 |
+
"ɔ̽˧˥": 36,
|
142 |
+
"tʰ": 37,
|
143 |
+
"i˥": 38,
|
144 |
+
"f": 39,
|
145 |
+
"aːĭ˧": 40,
|
146 |
+
"h": 41,
|
147 |
+
"ɵy˧": 42,
|
148 |
+
"a̞˥": 43,
|
149 |
+
"ei˧˩̰": 44,
|
150 |
+
"ou˨": 45,
|
151 |
+
"ɔ̽˧": 46,
|
152 |
+
"ɐi˧˩̰": 47,
|
153 |
+
"u˧": 48,
|
154 |
+
"ɔːĭ˥": 49,
|
155 |
+
"ɐu˨": 50,
|
156 |
+
"ei˧˥": 51,
|
157 |
+
"ɐi˨": 52,
|
158 |
+
"ʊ̟˧˩̰": 53,
|
159 |
+
"ʊ̟˨": 54,
|
160 |
+
"a̞˩˧": 55,
|
161 |
+
"ou˧˥": 56,
|
162 |
+
"aːĭ˧˥": 57,
|
163 |
+
"ɔ̽˨": 58,
|
164 |
+
"ɛ˩˧": 59,
|
165 |
+
"ɪ̞˨": 60,
|
166 |
+
"iːŭ˧": 61,
|
167 |
+
"ɛ˧˩̰": 62,
|
168 |
+
"m̩˧˩̰": 63,
|
169 |
+
"ɵ˧˥": 64,
|
170 |
+
"ei˧": 65,
|
171 |
+
"ɐu˧˩̰": 66,
|
172 |
+
"m̩˧": 67,
|
173 |
+
"ɐ˧˥": 68,
|
174 |
+
"ɐu˩˧": 69,
|
175 |
+
"ɐi˥": 70,
|
176 |
+
"ɔ̽˥": 71,
|
177 |
+
"ɔ̽˧˩̰": 72,
|
178 |
+
"ɔːĭ˧": 73,
|
179 |
+
"ou˩˧": 74,
|
180 |
+
"m̩˥": 75,
|
181 |
+
"ɐ˧": 76,
|
182 |
+
"tsʰ": 77,
|
183 |
+
"ɛ˧˥": 78,
|
184 |
+
"i˧˥": 79,
|
185 |
+
"ɔ̽˩˧": 80,
|
186 |
+
"kʰ": 81,
|
187 |
+
"ɐ˧˩̰": 82,
|
188 |
+
"aːŭ˧˥": 83,
|
189 |
+
"pʰ": 84,
|
190 |
+
"aːĭ˧˩̰": 85,
|
191 |
+
"ɵy˩˧": 86,
|
192 |
+
"ɛ˧": 87,
|
193 |
+
"u˧˥": 88,
|
194 |
+
"ɛ˨": 89,
|
195 |
+
"ʊ̟˧": 90,
|
196 |
+
"u˥": 91,
|
197 |
+
"m̩˩˧": 92,
|
198 |
+
"aːŭ˧": 93,
|
199 |
+
"œ̞˩˧": 94,
|
200 |
+
"i˩˧": 95,
|
201 |
+
"ɪ̞˧˩̰": 96,
|
202 |
+
"u˨": 97,
|
203 |
+
"ɪ̞˥": 98,
|
204 |
+
"iːŭ˧˩̰": 99,
|
205 |
+
"œ̞˧˥": 100,
|
206 |
+
"y˧": 101,
|
207 |
+
"uːĭ˩˧": 102,
|
208 |
+
"uːĭ˥": 103,
|
209 |
+
"ɵy˧˥": 104,
|
210 |
+
"y˧˩̰": 105,
|
211 |
+
"ɔːĭ˧˥": 106,
|
212 |
+
"ɛ": 107,
|
213 |
+
"ou˧": 108,
|
214 |
+
"ei˨": 109,
|
215 |
+
"ɵ˥": 110,
|
216 |
+
"u˧˩̰": 111,
|
217 |
+
"y˥": 112,
|
218 |
+
"œ̞˥": 113,
|
219 |
+
"œ̞˧˩̰": 114,
|
220 |
+
"aːĭ˨": 115,
|
221 |
+
"ɐ˩˧": 116,
|
222 |
+
"œ̞˧": 117,
|
223 |
+
"uːĭ˧˥": 118,
|
224 |
+
"ɐu˧": 119,
|
225 |
+
"ɐi˩˧": 120,
|
226 |
+
"ɐi˧": 121,
|
227 |
+
"ou˧˩̰": 122,
|
228 |
+
"aːĭ˥": 123,
|
229 |
+
"aːŭ˥": 124,
|
230 |
+
"ŋ˩˧": 125,
|
231 |
+
"y˧˥": 126,
|
232 |
+
"iːŭ˥": 127,
|
233 |
+
"ɔːĭ˨": 128,
|
234 |
+
"ʊ̟˧˥": 129,
|
235 |
+
"iːŭ˧˥": 130,
|
236 |
+
"ɵy˥": 131,
|
237 |
+
"ɔːĭ˧˩̰": 132,
|
238 |
+
"uːĭ˧": 133,
|
239 |
+
"ɵy˧˩̰": 134,
|
240 |
+
"œ̞˨": 135,
|
241 |
+
"m̩˨": 136,
|
242 |
+
"aːŭ˧˩̰": 137,
|
243 |
+
"y˩˧": 138,
|
244 |
+
"aːŭ˩˧": 139,
|
245 |
+
"aːĭ˩˧": 140,
|
246 |
+
"uːĭ˨": 141,
|
247 |
+
"ɵy˨": 142,
|
248 |
+
"aːŭ˨": 143,
|
249 |
+
"ɪ̞˧": 144,
|
250 |
+
"ɵ˨": 145,
|
251 |
"iːŭ˩˧": 146,
|
252 |
"iːŭ˨": 147,
|
253 |
+
"ɵ˧˩̰": 148,
|
254 |
"uːĭ˧˩̰": 149,
|
255 |
+
"u˩˧": 150,
|
256 |
+
"ŋ˧˩̰": 151
|
257 |
},
|
258 |
"unk_token": "UNK"
|
259 |
}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"UNK":0,"PAD":1,"WORD_BOUNDARY":2,"UTT_BOUNDARY":3,"
|
|
|
1 |
+
{"UNK":0,"PAD":1,"WORD_BOUNDARY":2,"UTT_BOUNDARY":3,"j":4,"ɐ˥":5,"t":6,"k":7,"ɐu˧˥":8,"i˨":9,"n":10,"i˧˩̰":11,"y˨":12,"s":13,"ɐ˨":14,"p":15,"ts":16,"ɐu˥":17,"ɪ̞˧˥":18,"ŋ":19,"ɵ˧":20,"a̞˧":21,"l":22,"ʊ̟˥":23,"a̞˧˩̰":24,"ɛ˥":25,"ei˩˧":26,"w":27,"a̞˨":28,"ɐi˧˥":29,"a̞˧˥":30,"m̩˧˥":31,"m":32,"ou˥":33,"ei˥":34,"i˧":35,"ɔ̽˧˥":36,"tʰ":37,"i˥":38,"f":39,"aːĭ˧":40,"h":41,"ɵy˧":42,"a̞˥":43,"ei˧˩̰":44,"ou˨":45,"ɔ̽˧":46,"ɐi˧˩̰":47,"u˧":48,"ɔːĭ˥":49,"ɐu˨":50,"ei˧˥":51,"ɐi˨":52,"ʊ̟˧˩̰":53,"ʊ̟˨":54,"a̞˩˧":55,"ou˧˥":56,"aːĭ˧˥":57,"ɔ̽˨":58,"ɛ˩˧":59,"ɪ̞˨":60,"iːŭ˧":61,"ɛ˧˩̰":62,"m̩˧˩̰":63,"ɵ˧˥":64,"ei˧":65,"ɐu˧˩̰":66,"m̩˧":67,"ɐ˧˥":68,"ɐu˩˧":69,"ɐi˥":70,"ɔ̽˥":71,"ɔ̽˧˩̰":72,"ɔːĭ˧":73,"ou˩˧":74,"m̩˥":75,"ɐ˧":76,"tsʰ":77,"ɛ˧˥":78,"i˧˥":79,"ɔ̽˩˧":80,"kʰ":81,"ɐ˧˩̰":82,"aːŭ˧˥":83,"pʰ":84,"aːĭ˧˩̰":85,"ɵy˩˧":86,"ɛ˧":87,"u˧˥":88,"ɛ˨":89,"ʊ̟˧":90,"u˥":91,"m̩˩˧":92,"aːŭ˧":93,"œ̞˩˧":94,"i˩˧":95,"ɪ̞˧˩̰":96,"u˨":97,"ɪ̞˥":98,"iːŭ˧˩̰":99,"œ̞˧˥":100,"y˧":101,"uːĭ˩˧":102,"uːĭ˥":103,"ɵy˧˥":104,"y˧˩̰":105,"ɔːĭ˧˥":106,"ɛ":107,"ou˧":108,"ei˨":109,"ɵ˥":110,"u˧˩̰":111,"y˥":112,"œ̞˥":113,"œ̞˧˩̰":114,"aːĭ˨":115,"ɐ˩˧":116,"œ̞˧":117,"uːĭ˧˥":118,"ɐu˧":119,"ɐi˩˧":120,"ɐi˧":121,"ou˧˩̰":122,"aːĭ˥":123,"aːŭ˥":124,"ŋ˩˧":125,"y˧˥":126,"iːŭ˥":127,"ɔːĭ˨":128,"ʊ̟˧˥":129,"iːŭ˧˥":130,"ɵy˥":131,"ɔːĭ˧˩̰":132,"uːĭ˧":133,"ɵy˧˩̰":134,"œ̞˨":135,"m̩˨":136,"aːŭ˧˩̰":137,"y˩˧":138,"aːŭ˩˧":139,"aːĭ˩˧":140,"uːĭ˨":141,"ɵy˨":142,"aːŭ˨":143,"ɪ̞˧":144,"ɵ˨":145,"iːŭ˩˧":146,"iːŭ˨":147,"ɵ˧˩̰":148,"uːĭ˧˩̰":149,"u˩˧":150,"ŋ˧˩̰":151}
|