jz703 commited on
Commit
4ffcb2e
1 Parent(s): c2ce986

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +43 -0
  2. special_tokens_map.json +6 -0
  3. tokenizer_config.json +344 -0
  4. vocab.json +75 -0
added_tokens.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 74,
3
+ "<s>": 73,
4
+ "[PAD]": 72,
5
+ "[UNK]": 71,
6
+ "aɪ": 8,
7
+ "aʊ": 63,
8
+ "d͡ʒ": 69,
9
+ "eɪ": 38,
10
+ "oʊ": 9,
11
+ "t͡ʃ": 35,
12
+ "ɔɪ": 28,
13
+ "ˈaɪ": 33,
14
+ "ˈaʊ": 26,
15
+ "ˈeɪ": 48,
16
+ "ˈi": 34,
17
+ "ˈoʊ": 62,
18
+ "ˈu": 50,
19
+ "ˈæ": 36,
20
+ "ˈɑ": 17,
21
+ "ˈɔ": 21,
22
+ "ˈɔɪ": 59,
23
+ "ˈɚ": 57,
24
+ "ˈɛ": 22,
25
+ "ˈɪ": 19,
26
+ "ˈʊ": 5,
27
+ "ˈʌ": 41,
28
+ "ˌaɪ": 13,
29
+ "ˌaʊ": 53,
30
+ "ˌeɪ": 45,
31
+ "ˌi": 24,
32
+ "ˌoʊ": 32,
33
+ "ˌu": 11,
34
+ "ˌæ": 42,
35
+ "ˌɑ": 14,
36
+ "ˌɔ": 66,
37
+ "ˌɔɪ": 65,
38
+ "ˌɚ": 31,
39
+ "ˌɛ": 20,
40
+ "ˌɪ": 52,
41
+ "ˌʊ": 4,
42
+ "ˌʌ": 46
43
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "4": {
4
+ "content": "ˌʊ",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "5": {
12
+ "content": "ˈʊ",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "8": {
20
+ "content": "aɪ",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "9": {
28
+ "content": "oʊ",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "11": {
36
+ "content": "ˌu",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "13": {
44
+ "content": "ˌaɪ",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "14": {
52
+ "content": "ˌɑ",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "17": {
60
+ "content": "ˈɑ",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "19": {
68
+ "content": "ˈɪ",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "20": {
76
+ "content": "ˌɛ",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "21": {
84
+ "content": "ˈɔ",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "22": {
92
+ "content": "ˈɛ",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "24": {
100
+ "content": "ˌi",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "26": {
108
+ "content": "ˈaʊ",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "28": {
116
+ "content": "ɔɪ",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "31": {
124
+ "content": "ˌɚ",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "32": {
132
+ "content": "ˌoʊ",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "33": {
140
+ "content": "ˈaɪ",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "34": {
148
+ "content": "ˈi",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "35": {
156
+ "content": "t͡ʃ",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "36": {
164
+ "content": "ˈæ",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "38": {
172
+ "content": "eɪ",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "41": {
180
+ "content": "ˈʌ",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "42": {
188
+ "content": "ˌæ",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "45": {
196
+ "content": "ˌeɪ",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "46": {
204
+ "content": "ˌʌ",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "48": {
212
+ "content": "ˈeɪ",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50": {
220
+ "content": "ˈu",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "52": {
228
+ "content": "ˌɪ",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "53": {
236
+ "content": "ˌaʊ",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "57": {
244
+ "content": "ˈɚ",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "59": {
252
+ "content": "ˈɔɪ",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "62": {
260
+ "content": "ˈoʊ",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "63": {
268
+ "content": "aʊ",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "65": {
276
+ "content": "ˌɔɪ",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "66": {
284
+ "content": "ˌɔ",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "69": {
292
+ "content": "d͡ʒ",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "71": {
300
+ "content": "[UNK]",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "72": {
308
+ "content": "[PAD]",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "73": {
316
+ "content": "<s>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "74": {
324
+ "content": "</s>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ }
331
+ },
332
+ "additional_special_tokens": [],
333
+ "bos_token": "<s>",
334
+ "clean_up_tokenization_spaces": true,
335
+ "do_lower_case": false,
336
+ "eos_token": "</s>",
337
+ "model_max_length": 1000000000000000019884624838656,
338
+ "pad_token": "[PAD]",
339
+ "replace_word_delimiter_char": " ",
340
+ "target_lang": null,
341
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
342
+ "unk_token": "[UNK]",
343
+ "word_delimiter_token": "|"
344
+ }
vocab.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 72,
3
+ "[UNK]": 71,
4
+ "aɪ": 8,
5
+ "aʊ": 63,
6
+ "b": 37,
7
+ "d": 15,
8
+ "d͡ʒ": 69,
9
+ "eɪ": 38,
10
+ "f": 51,
11
+ "h": 70,
12
+ "i": 61,
13
+ "j": 67,
14
+ "k": 2,
15
+ "l": 25,
16
+ "m": 29,
17
+ "n": 39,
18
+ "oʊ": 9,
19
+ "p": 23,
20
+ "s": 55,
21
+ "t": 49,
22
+ "t͡ʃ": 35,
23
+ "u": 16,
24
+ "v": 44,
25
+ "w": 12,
26
+ "z": 1,
27
+ "|": 0,
28
+ "æ": 27,
29
+ "ð": 18,
30
+ "ŋ": 54,
31
+ "ɑ": 60,
32
+ "ɔ": 30,
33
+ "ɔɪ": 28,
34
+ "ə": 7,
35
+ "ɚ": 47,
36
+ "ɛ": 58,
37
+ "ɡ": 3,
38
+ "ɪ": 56,
39
+ "ɹ": 40,
40
+ "ʃ": 68,
41
+ "ʊ": 6,
42
+ "ʌ": 10,
43
+ "ʒ": 43,
44
+ "ˈaɪ": 33,
45
+ "ˈaʊ": 26,
46
+ "ˈeɪ": 48,
47
+ "ˈi": 34,
48
+ "ˈoʊ": 62,
49
+ "ˈu": 50,
50
+ "ˈæ": 36,
51
+ "ˈɑ": 17,
52
+ "ˈɔ": 21,
53
+ "ˈɔɪ": 59,
54
+ "ˈɚ": 57,
55
+ "ˈɛ": 22,
56
+ "ˈɪ": 19,
57
+ "ˈʊ": 5,
58
+ "ˈʌ": 41,
59
+ "ˌaɪ": 13,
60
+ "ˌaʊ": 53,
61
+ "ˌeɪ": 45,
62
+ "ˌi": 24,
63
+ "ˌoʊ": 32,
64
+ "ˌu": 11,
65
+ "ˌæ": 42,
66
+ "ˌɑ": 14,
67
+ "ˌɔ": 66,
68
+ "ˌɔɪ": 65,
69
+ "ˌɚ": 31,
70
+ "ˌɛ": 20,
71
+ "ˌɪ": 52,
72
+ "ˌʊ": 4,
73
+ "ˌʌ": 46,
74
+ "θ": 64
75
+ }