codebyzeb commited on
Commit
60145ac
·
verified ·
1 Parent(s): 09eaaab

Upload tokenizer

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