Hugging Face's logo

pinot
/
wav2vec2-conformer-cv-15

Model card Files Community
pinot commited on
Commit
5e66999
•
1 Parent(s): c1d6c40

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +247 -0
  3. vocab.json +56 -0
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 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "11": {
36
+ "content": "kj",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "12": {
44
+ "content": "ky",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "13": {
52
+ "content": "kw",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "15": {
60
+ "content": "sj",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "16": {
68
+ "content": "sy",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "18": {
76
+ "content": "cj",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "20": {
84
+ "content": "cy",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "22": {
92
+ "content": "nj",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "23": {
100
+ "content": "ny",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "25": {
108
+ "content": "hj",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "26": {
116
+ "content": "hy",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "29": {
124
+ "content": "my",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "32": {
132
+ "content": "ry",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "37": {
140
+ "content": "gj",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "38": {
148
+ "content": "gy",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "39": {
156
+ "content": "gw",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "41": {
164
+ "content": "zj",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "42": {
172
+ "content": "zy",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "45": {
180
+ "content": "by",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "47": {
188
+ "content": "py",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "48": {
196
+ "content": "aH",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "49": {
204
+ "content": "iH",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50": {
212
+ "content": "uH",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "51": {
220
+ "content": "eH",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "52": {
228
+ "content": "oH",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ }
235
+ },
236
+ "bos_token": "<s>",
237
+ "clean_up_tokenization_spaces": true,
238
+ "do_lower_case": false,
239
+ "eos_token": "</s>",
240
+ "model_max_length": 1000000000000000019884624838656,
241
+ "pad_token": "<pad>",
242
+ "replace_word_delimiter_char": " ",
243
+ "target_lang": null,
244
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
245
+ "unk_token": "<unk>",
246
+ "word_delimiter_token": "|"
247
+ }
vocab.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<pad>": 0,
4
+ "<s>": 1,
5
+ "<unk>": 3,
6
+ "F": 27,
7
+ "N": 34,
8
+ "Q": 35,
9
+ "a": 5,
10
+ "aH": 48,
11
+ "b": 44,
12
+ "by": 45,
13
+ "c": 19,
14
+ "cj": 18,
15
+ "cy": 20,
16
+ "d": 43,
17
+ "e": 8,
18
+ "eH": 51,
19
+ "g": 36,
20
+ "gj": 37,
21
+ "gw": 39,
22
+ "gy": 38,
23
+ "h": 24,
24
+ "hj": 25,
25
+ "hy": 26,
26
+ "i": 6,
27
+ "iH": 49,
28
+ "k": 10,
29
+ "kj": 11,
30
+ "kw": 13,
31
+ "ky": 12,
32
+ "m": 28,
33
+ "my": 29,
34
+ "n": 21,
35
+ "nj": 22,
36
+ "ny": 23,
37
+ "o": 9,
38
+ "oH": 52,
39
+ "p": 46,
40
+ "py": 47,
41
+ "r": 31,
42
+ "ry": 32,
43
+ "s": 14,
44
+ "sj": 15,
45
+ "sy": 16,
46
+ "t": 17,
47
+ "u": 7,
48
+ "uH": 50,
49
+ "v": 53,
50
+ "w": 33,
51
+ "y": 30,
52
+ "z": 40,
53
+ "zj": 41,
54
+ "zy": 42,
55
+ "|": 4
56
+ }