Hugging Face's logo

gary109
/
ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
gary109/AI_Light_Dance
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
gary109 commited on
Commit
dfe3758
•
1 Parent(s): 9357af2

Upload lm-boosted decoder new

Browse files
Files changed (8) hide show
  1. added_tokens.json +4 -0
  2. alphabet.json +1 -0
  3. language_model/5gram_correct.arpa +0 -0
  4. language_model/attrs.json +1 -0
  5. language_model/unigrams.txt +89 -0
  6. special_tokens_map.json +288 -0
  7. tokenizer_config.json +14 -0
  8. vocab.json +18 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
1
+ {
2
+ "</s>": 17,
3
+ "<s>": 16
4
+ }
alphabet.json ADDED
@@ -0,0 +1 @@
 
1
+ {"labels": [" ", "#", "1", "2", "3", "4", "5", "a", "b", "c", "d", "e", "f", "g", "\u2047", "", "<s>", "</s>"], "is_bpe": false}
language_model/5gram_correct.arpa ADDED
The diff for this file is too large to render. See raw diff
language_model/attrs.json ADDED
@@ -0,0 +1 @@
 
1
+ {"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}
language_model/unigrams.txt ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ </s>
2
+ <s>
3
+ a#2
4
+ a#2.
5
+ a#3
6
+ a#3.
7
+ a#4
8
+ a#4.
9
+ a#5
10
+ a#5.
11
+ a1
12
+ a2
13
+ a2.
14
+ a3
15
+ a3.
16
+ a4
17
+ a4.
18
+ a5
19
+ b2
20
+ b2.
21
+ b3
22
+ b3.
23
+ b4
24
+ b4.
25
+ b5
26
+ c#3
27
+ c#3.
28
+ c#4
29
+ c#4.
30
+ c#5
31
+ c#5.
32
+ c3
33
+ c3.
34
+ c4
35
+ c4.
36
+ c5
37
+ c5.
38
+ d#3
39
+ d#3.
40
+ d#4
41
+ d#4.
42
+ d#5
43
+ d#5.
44
+ d2
45
+ d3
46
+ d3.
47
+ d4
48
+ d4.
49
+ d5
50
+ d5.
51
+ e2
52
+ e2.
53
+ e3
54
+ e3.
55
+ e4
56
+ e4.
57
+ e5
58
+ e5.
59
+ f#2
60
+ f#2.
61
+ f#3
62
+ f#3.
63
+ f#4
64
+ f#4.
65
+ f#5
66
+ f#5.
67
+ f1
68
+ f2
69
+ f3
70
+ f3.
71
+ f4
72
+ f4.
73
+ f5
74
+ f5.
75
+ g#2
76
+ g#2.
77
+ g#3
78
+ g#3.
79
+ g#4
80
+ g#4.
81
+ g#5
82
+ g#5.
83
+ g2
84
+ g2.
85
+ g3
86
+ g3.
87
+ g4
88
+ g4.
89
+ g5
special_tokens_map.json ADDED
@@ -0,0 +1,288 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s>",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s>",
68
+ "lstrip": false,
69
+ "normalized": true,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s>",
75
+ "lstrip": false,
76
+ "normalized": true,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "</s>",
82
+ "lstrip": false,
83
+ "normalized": true,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<s>",
89
+ "lstrip": false,
90
+ "normalized": true,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "</s>",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<s>",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "</s>",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<s>",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "</s>",
124
+ "lstrip": false,
125
+ "normalized": true,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<s>",
131
+ "lstrip": false,
132
+ "normalized": true,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "</s>",
138
+ "lstrip": false,
139
+ "normalized": true,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<s>",
145
+ "lstrip": false,
146
+ "normalized": true,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "</s>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<s>",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "</s>",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<s>",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "</s>",
180
+ "lstrip": false,
181
+ "normalized": true,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<s>",
187
+ "lstrip": false,
188
+ "normalized": true,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "</s>",
194
+ "lstrip": false,
195
+ "normalized": true,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<s>",
201
+ "lstrip": false,
202
+ "normalized": true,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "</s>",
208
+ "lstrip": false,
209
+ "normalized": true,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<s>",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "</s>",
222
+ "lstrip": false,
223
+ "normalized": true,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<s>",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "</s>",
236
+ "lstrip": false,
237
+ "normalized": true,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<s>",
243
+ "lstrip": false,
244
+ "normalized": true,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "</s>",
250
+ "lstrip": false,
251
+ "normalized": true,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<s>",
257
+ "lstrip": false,
258
+ "normalized": true,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "</s>",
264
+ "lstrip": false,
265
+ "normalized": true,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<s>",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "</s>",
278
+ "lstrip": false,
279
+ "normalized": true,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ }
283
+ ],
284
+ "bos_token": "<s>",
285
+ "eos_token": "</s>",
286
+ "pad_token": "[PAD]",
287
+ "unk_token": "[UNK]"
288
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "name_or_path": "gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1",
6
+ "pad_token": "[PAD]",
7
+ "processor_class": "Wav2Vec2ProcessorWithLM",
8
+ "replace_word_delimiter_char": " ",
9
+ "special_tokens_map_file": null,
10
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
11
+ "trust_remote_code": false,
12
+ "unk_token": "[UNK]",
13
+ "word_delimiter_token": "|"
14
+ }
vocab.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "#": 1,
3
+ "1": 2,
4
+ "2": 3,
5
+ "3": 4,
6
+ "4": 5,
7
+ "5": 6,
8
+ "[PAD]": 15,
9
+ "[UNK]": 14,
10
+ "a": 7,
11
+ "b": 8,
12
+ "c": 9,
13
+ "d": 10,
14
+ "e": 11,
15
+ "f": 12,
16
+ "g": 13,
17
+ "|": 0
18
+ }