molto commited on
Commit
4d3eeb6
β€’
1 Parent(s): ecf49a0

Upload 10 files

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ft_kor_test_1
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # ft_kor_test_1
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0205
18
+ - Cer: 0.0037
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 20
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
50
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
51
+ | 5.8814 | 0.1 | 500 | 3.3282 | 1.0 |
52
+ | 2.922 | 0.2 | 1000 | 1.5452 | 0.4197 |
53
+ | 1.0454 | 0.3 | 1500 | 0.5135 | 0.1411 |
54
+ | 0.6881 | 0.4 | 2000 | 0.3212 | 0.0964 |
55
+ | 0.5735 | 0.51 | 2500 | 0.2526 | 0.0805 |
56
+ | 0.5236 | 0.61 | 3000 | 0.2255 | 0.0691 |
57
+ | 0.4813 | 0.71 | 3500 | 0.2167 | 0.0662 |
58
+ | 0.4442 | 0.81 | 4000 | 0.1816 | 0.0575 |
59
+ | 0.4244 | 0.91 | 4500 | 0.1717 | 0.0542 |
60
+ | 0.4026 | 1.01 | 5000 | 0.1573 | 0.0525 |
61
+ | 0.3691 | 1.11 | 5500 | 0.1423 | 0.0455 |
62
+ | 0.3606 | 1.21 | 6000 | 0.1340 | 0.0429 |
63
+ | 0.3451 | 1.32 | 6500 | 0.1305 | 0.0417 |
64
+ | 0.3421 | 1.42 | 7000 | 0.1231 | 0.0389 |
65
+ | 0.3319 | 1.52 | 7500 | 0.1167 | 0.0379 |
66
+ | 0.3265 | 1.62 | 8000 | 0.1158 | 0.0373 |
67
+ | 0.3114 | 1.72 | 8500 | 0.1105 | 0.0343 |
68
+ | 0.299 | 1.82 | 9000 | 0.1015 | 0.0322 |
69
+ | 0.3023 | 1.92 | 9500 | 0.0968 | 0.0309 |
70
+ | 0.2952 | 2.02 | 10000 | 0.0926 | 0.0301 |
71
+ | 0.2719 | 2.13 | 10500 | 0.0937 | 0.0297 |
72
+ | 0.2726 | 2.23 | 11000 | 0.0902 | 0.0285 |
73
+ | 0.2615 | 2.33 | 11500 | 0.0876 | 0.0284 |
74
+ | 0.2611 | 2.43 | 12000 | 0.0839 | 0.0264 |
75
+ | 0.2505 | 2.53 | 12500 | 0.0848 | 0.0269 |
76
+ | 0.2494 | 2.63 | 13000 | 0.0788 | 0.0246 |
77
+ | 0.2442 | 2.73 | 13500 | 0.0798 | 0.0249 |
78
+ | 0.2448 | 2.83 | 14000 | 0.0769 | 0.0243 |
79
+ | 0.2365 | 2.93 | 14500 | 0.0755 | 0.0240 |
80
+ | 0.234 | 3.04 | 15000 | 0.0750 | 0.0221 |
81
+ | 0.2282 | 3.14 | 15500 | 0.0717 | 0.0219 |
82
+ | 0.2173 | 3.24 | 16000 | 0.0673 | 0.0210 |
83
+ | 0.2124 | 3.34 | 16500 | 0.0680 | 0.0211 |
84
+ | 0.2161 | 3.44 | 17000 | 0.0656 | 0.0206 |
85
+ | 0.2089 | 3.54 | 17500 | 0.0664 | 0.0204 |
86
+ | 0.213 | 3.64 | 18000 | 0.0623 | 0.0190 |
87
+ | 0.2094 | 3.74 | 18500 | 0.0635 | 0.0184 |
88
+ | 0.1998 | 3.85 | 19000 | 0.0635 | 0.0184 |
89
+ | 0.2024 | 3.95 | 19500 | 0.0620 | 0.0183 |
90
+ | 0.1935 | 4.05 | 20000 | 0.0572 | 0.0174 |
91
+ | 0.1873 | 4.15 | 20500 | 0.0607 | 0.0180 |
92
+ | 0.1789 | 4.25 | 21000 | 0.0583 | 0.0163 |
93
+ | 0.1842 | 4.35 | 21500 | 0.0663 | 0.0187 |
94
+ | 0.1773 | 4.45 | 22000 | 0.0532 | 0.0156 |
95
+ | 0.1877 | 4.55 | 22500 | 0.0583 | 0.0163 |
96
+ | 0.1844 | 4.65 | 23000 | 0.0543 | 0.0155 |
97
+ | 0.1711 | 4.76 | 23500 | 0.0522 | 0.0150 |
98
+ | 0.1703 | 4.86 | 24000 | 0.0503 | 0.0148 |
99
+ | 0.1712 | 4.96 | 24500 | 0.0524 | 0.0153 |
100
+ | 0.1642 | 5.06 | 25000 | 0.0505 | 0.0148 |
101
+ | 0.1622 | 5.16 | 25500 | 0.0476 | 0.0138 |
102
+ | 0.1544 | 5.26 | 26000 | 0.0500 | 0.0143 |
103
+ | 0.157 | 5.36 | 26500 | 0.0505 | 0.0139 |
104
+ | 0.1632 | 5.46 | 27000 | 0.0487 | 0.0138 |
105
+ | 0.1516 | 5.57 | 27500 | 0.0440 | 0.0126 |
106
+ | 0.1532 | 5.67 | 28000 | 0.0467 | 0.0127 |
107
+ | 0.1523 | 5.77 | 28500 | 0.0486 | 0.0135 |
108
+ | 0.1471 | 5.87 | 29000 | 0.0489 | 0.0129 |
109
+ | 0.1498 | 5.97 | 29500 | 0.0458 | 0.0123 |
110
+ | 0.1511 | 6.07 | 30000 | 0.0424 | 0.0123 |
111
+ | 0.1422 | 6.17 | 30500 | 0.0444 | 0.0118 |
112
+ | 0.1394 | 6.27 | 31000 | 0.0519 | 0.0148 |
113
+ | 0.1483 | 6.38 | 31500 | 0.0436 | 0.0120 |
114
+ | 0.1394 | 6.48 | 32000 | 0.0465 | 0.0126 |
115
+ | 0.1363 | 6.58 | 32500 | 0.0397 | 0.0110 |
116
+ | 0.1372 | 6.68 | 33000 | 0.0418 | 0.0110 |
117
+ | 0.1353 | 6.78 | 33500 | 0.0412 | 0.0110 |
118
+ | 0.1356 | 6.88 | 34000 | 0.0397 | 0.0109 |
119
+ | 0.1321 | 6.98 | 34500 | 0.0380 | 0.0100 |
120
+ | 0.1323 | 7.08 | 35000 | 0.0373 | 0.0101 |
121
+ | 0.1251 | 7.18 | 35500 | 0.0365 | 0.0099 |
122
+ | 0.1238 | 7.29 | 36000 | 0.0381 | 0.0100 |
123
+ | 0.1247 | 7.39 | 36500 | 0.0394 | 0.0103 |
124
+ | 0.128 | 7.49 | 37000 | 0.0389 | 0.0102 |
125
+ | 0.1245 | 7.59 | 37500 | 0.0382 | 0.0096 |
126
+ | 0.1224 | 7.69 | 38000 | 0.0358 | 0.0090 |
127
+ | 0.12 | 7.79 | 38500 | 0.0495 | 0.0113 |
128
+ | 0.1217 | 7.89 | 39000 | 0.0476 | 0.0108 |
129
+ | 0.1198 | 7.99 | 39500 | 0.0512 | 0.0130 |
130
+ | 0.1125 | 8.1 | 40000 | 0.0431 | 0.0109 |
131
+ | 0.1107 | 8.2 | 40500 | 0.0456 | 0.0111 |
132
+ | 0.1101 | 8.3 | 41000 | 0.0889 | 0.0176 |
133
+ | 0.1136 | 8.4 | 41500 | 0.0449 | 0.0103 |
134
+ | 0.1131 | 8.5 | 42000 | 0.0320 | 0.0082 |
135
+ | 0.1145 | 8.6 | 42500 | 0.0311 | 0.0083 |
136
+ | 0.1039 | 8.7 | 43000 | 0.0317 | 0.0086 |
137
+ | 0.1115 | 8.8 | 43500 | 0.0384 | 0.0086 |
138
+ | 0.1098 | 8.91 | 44000 | 0.0328 | 0.0085 |
139
+ | 0.1114 | 9.01 | 44500 | 0.0331 | 0.0083 |
140
+ | 0.0982 | 9.11 | 45000 | 0.0305 | 0.0079 |
141
+ | 0.1041 | 9.21 | 45500 | 0.0359 | 0.0084 |
142
+ | 0.1033 | 9.31 | 46000 | 0.0298 | 0.0076 |
143
+ | 0.1024 | 9.41 | 46500 | 0.0310 | 0.0076 |
144
+ | 0.0981 | 9.51 | 47000 | 0.0309 | 0.0075 |
145
+ | 0.1033 | 9.61 | 47500 | 0.0311 | 0.0076 |
146
+ | 0.0995 | 9.71 | 48000 | 0.0309 | 0.0079 |
147
+ | 0.1012 | 9.82 | 48500 | 0.0283 | 0.0071 |
148
+ | 0.1039 | 9.92 | 49000 | 0.0276 | 0.0070 |
149
+ | 0.0957 | 10.02 | 49500 | 0.0298 | 0.0071 |
150
+ | 0.0933 | 10.12 | 50000 | 0.0297 | 0.0073 |
151
+ | 0.0961 | 10.22 | 50500 | 0.0278 | 0.0069 |
152
+ | 0.0939 | 10.32 | 51000 | 0.0278 | 0.0071 |
153
+ | 0.0928 | 10.42 | 51500 | 0.0279 | 0.0071 |
154
+ | 0.0915 | 10.52 | 52000 | 0.0271 | 0.0065 |
155
+ | 0.0907 | 10.63 | 52500 | 0.0385 | 0.0099 |
156
+ | 0.0951 | 10.73 | 53000 | 0.0556 | 0.0127 |
157
+ | 0.0949 | 10.83 | 53500 | 0.0767 | 0.0189 |
158
+ | 0.0923 | 10.93 | 54000 | 0.0317 | 0.0074 |
159
+ | 0.0852 | 11.03 | 54500 | 0.0474 | 0.0114 |
160
+ | 0.0863 | 11.13 | 55000 | 0.0304 | 0.0067 |
161
+ | 0.0858 | 11.23 | 55500 | 0.0289 | 0.0063 |
162
+ | 0.0852 | 11.33 | 56000 | 0.0399 | 0.0117 |
163
+ | 0.0821 | 11.43 | 56500 | 0.0498 | 0.0111 |
164
+ | 0.0822 | 11.54 | 57000 | 0.0452 | 0.0113 |
165
+ | 0.0838 | 11.64 | 57500 | 0.0397 | 0.0079 |
166
+ | 0.0771 | 11.74 | 58000 | 0.0568 | 0.0120 |
167
+ | 0.0813 | 11.84 | 58500 | 0.0465 | 0.0087 |
168
+ | 0.078 | 11.94 | 59000 | 0.0524 | 0.0092 |
169
+ | 0.0809 | 12.04 | 59500 | 0.0545 | 0.0100 |
170
+ | 0.0755 | 12.14 | 60000 | 0.0273 | 0.0057 |
171
+ | 0.077 | 12.24 | 60500 | 0.0277 | 0.0060 |
172
+ | 0.0772 | 12.35 | 61000 | 0.0265 | 0.0057 |
173
+ | 0.0728 | 12.45 | 61500 | 0.0311 | 0.0057 |
174
+ | 0.0766 | 12.55 | 62000 | 0.0301 | 0.0066 |
175
+ | 0.0805 | 12.65 | 62500 | 0.0323 | 0.0067 |
176
+ | 0.0732 | 12.75 | 63000 | 0.0298 | 0.0061 |
177
+ | 0.0735 | 12.85 | 63500 | 0.0229 | 0.0052 |
178
+ | 0.0738 | 12.95 | 64000 | 0.0242 | 0.0054 |
179
+ | 0.0709 | 13.05 | 64500 | 0.0237 | 0.0053 |
180
+ | 0.0702 | 13.16 | 65000 | 0.0236 | 0.0050 |
181
+ | 0.0702 | 13.26 | 65500 | 0.0255 | 0.0053 |
182
+ | 0.0676 | 13.36 | 66000 | 0.0236 | 0.0052 |
183
+ | 0.0704 | 13.46 | 66500 | 0.0224 | 0.0053 |
184
+ | 0.07 | 13.56 | 67000 | 0.0238 | 0.0054 |
185
+ | 0.0671 | 13.66 | 67500 | 0.0232 | 0.0054 |
186
+ | 0.0709 | 13.76 | 68000 | 0.0228 | 0.0051 |
187
+ | 0.0636 | 13.86 | 68500 | 0.0227 | 0.0052 |
188
+ | 0.0661 | 13.96 | 69000 | 0.0223 | 0.0049 |
189
+ | 0.0645 | 14.07 | 69500 | 0.0222 | 0.0048 |
190
+ | 0.0639 | 14.17 | 70000 | 0.0243 | 0.0051 |
191
+ | 0.0608 | 14.27 | 70500 | 0.0250 | 0.0050 |
192
+ | 0.0631 | 14.37 | 71000 | 0.0234 | 0.0048 |
193
+ | 0.0656 | 14.47 | 71500 | 0.0228 | 0.0048 |
194
+ | 0.0616 | 14.57 | 72000 | 0.0239 | 0.0050 |
195
+ | 0.0631 | 14.67 | 72500 | 0.0237 | 0.0049 |
196
+ | 0.0662 | 14.77 | 73000 | 0.0234 | 0.0047 |
197
+ | 0.0622 | 14.88 | 73500 | 0.0289 | 0.0056 |
198
+ | 0.064 | 14.98 | 74000 | 0.0242 | 0.0048 |
199
+ | 0.0546 | 15.08 | 74500 | 0.0234 | 0.0049 |
200
+ | 0.0573 | 15.18 | 75000 | 0.0254 | 0.0054 |
201
+ | 0.0571 | 15.28 | 75500 | 0.0288 | 0.0058 |
202
+ | 0.0576 | 15.38 | 76000 | 0.0244 | 0.0053 |
203
+ | 0.0562 | 15.48 | 76500 | 0.0299 | 0.0061 |
204
+ | 0.0595 | 15.58 | 77000 | 0.0221 | 0.0046 |
205
+ | 0.0601 | 15.69 | 77500 | 0.0224 | 0.0046 |
206
+ | 0.0575 | 15.79 | 78000 | 0.0216 | 0.0045 |
207
+ | 0.059 | 15.89 | 78500 | 0.0222 | 0.0045 |
208
+ | 0.0562 | 15.99 | 79000 | 0.0224 | 0.0047 |
209
+ | 0.0551 | 16.09 | 79500 | 0.0216 | 0.0044 |
210
+ | 0.0539 | 16.19 | 80000 | 0.0223 | 0.0047 |
211
+ | 0.0547 | 16.29 | 80500 | 0.0212 | 0.0045 |
212
+ | 0.0527 | 16.39 | 81000 | 0.0264 | 0.0049 |
213
+ | 0.0527 | 16.49 | 81500 | 0.0247 | 0.0050 |
214
+ | 0.0526 | 16.6 | 82000 | 0.0236 | 0.0047 |
215
+ | 0.0507 | 16.7 | 82500 | 0.0213 | 0.0042 |
216
+ | 0.0522 | 16.8 | 83000 | 0.0221 | 0.0042 |
217
+ | 0.0522 | 16.9 | 83500 | 0.0220 | 0.0042 |
218
+ | 0.0496 | 17.0 | 84000 | 0.0217 | 0.0043 |
219
+ | 0.0495 | 17.1 | 84500 | 0.0214 | 0.0042 |
220
+ | 0.0493 | 17.2 | 85000 | 0.0217 | 0.0042 |
221
+ | 0.0488 | 17.3 | 85500 | 0.0207 | 0.0040 |
222
+ | 0.0492 | 17.41 | 86000 | 0.0210 | 0.0042 |
223
+ | 0.0496 | 17.51 | 86500 | 0.0204 | 0.0042 |
224
+ | 0.0487 | 17.61 | 87000 | 0.0216 | 0.0041 |
225
+ | 0.0466 | 17.71 | 87500 | 0.0199 | 0.0040 |
226
+ | 0.0465 | 17.81 | 88000 | 0.0199 | 0.0040 |
227
+ | 0.0491 | 17.91 | 88500 | 0.0198 | 0.0040 |
228
+ | 0.0469 | 18.01 | 89000 | 0.0204 | 0.0041 |
229
+ | 0.0447 | 18.11 | 89500 | 0.0205 | 0.0040 |
230
+ | 0.0487 | 18.21 | 90000 | 0.0215 | 0.0040 |
231
+ | 0.0455 | 18.32 | 90500 | 0.0207 | 0.0039 |
232
+ | 0.047 | 18.42 | 91000 | 0.0207 | 0.0040 |
233
+ | 0.0458 | 18.52 | 91500 | 0.0206 | 0.0040 |
234
+ | 0.0462 | 18.62 | 92000 | 0.0202 | 0.0039 |
235
+ | 0.0473 | 18.72 | 92500 | 0.0212 | 0.0039 |
236
+ | 0.043 | 18.82 | 93000 | 0.0208 | 0.0039 |
237
+ | 0.0435 | 18.92 | 93500 | 0.0204 | 0.0039 |
238
+ | 0.0448 | 19.02 | 94000 | 0.0208 | 0.0038 |
239
+ | 0.0435 | 19.13 | 94500 | 0.0205 | 0.0038 |
240
+ | 0.0433 | 19.23 | 95000 | 0.0203 | 0.0038 |
241
+ | 0.0425 | 19.33 | 95500 | 0.0204 | 0.0037 |
242
+ | 0.045 | 19.43 | 96000 | 0.0205 | 0.0038 |
243
+ | 0.043 | 19.53 | 96500 | 0.0205 | 0.0037 |
244
+ | 0.0435 | 19.63 | 97000 | 0.0206 | 0.0038 |
245
+ | 0.0424 | 19.73 | 97500 | 0.0207 | 0.0037 |
246
+ | 0.0441 | 19.83 | 98000 | 0.0206 | 0.0037 |
247
+ | 0.0452 | 19.94 | 98500 | 0.0205 | 0.0037 |
248
+
249
+
250
+ ### Framework versions
251
+
252
+ - Transformers 4.29.2
253
+ - Pytorch 2.0.1+cu117
254
+ - Datasets 2.13.0
255
+ - Tokenizers 0.13.3
config.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.0,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.1,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "gradient_checkpointing": false,
56
+ "hidden_act": "gelu",
57
+ "hidden_dropout": 0.1,
58
+ "hidden_size": 1024,
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "layer_norm_eps": 1e-05,
62
+ "layerdrop": 0.1,
63
+ "mask_feature_length": 10,
64
+ "mask_feature_min_masks": 0,
65
+ "mask_feature_prob": 0.0,
66
+ "mask_time_length": 10,
67
+ "mask_time_min_masks": 2,
68
+ "mask_time_prob": 0.075,
69
+ "model_type": "wav2vec2",
70
+ "num_adapter_layers": 3,
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "output_hidden_size": 1024,
80
+ "pad_token_id": 49,
81
+ "proj_codevector_dim": 768,
82
+ "tdnn_dilation": [
83
+ 1,
84
+ 2,
85
+ 3,
86
+ 1,
87
+ 1
88
+ ],
89
+ "tdnn_dim": [
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 512,
94
+ 1500
95
+ ],
96
+ "tdnn_kernel": [
97
+ 5,
98
+ 3,
99
+ 3,
100
+ 1,
101
+ 1
102
+ ],
103
+ "torch_dtype": "float32",
104
+ "transformers_version": "4.29.2",
105
+ "use_weighted_layer_sum": false,
106
+ "vocab_size": 50,
107
+ "xvector_output_dim": 512
108
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8e79b7e5a70f69a55e11f9215a121a305da5d610cd57841a75a2dfea167a5e
3
+ size 1262106861
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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "do_lower_case": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "[PAD]",
8
+ "replace_word_delimiter_char": " ",
9
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
10
+ "unk_token": "[UNK]",
11
+ "word_delimiter_token": "|"
12
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2459b73027e2b21d2411d029af9753d482a69a4513b1953ab3bb1695cbb3b85e
3
+ size 3899
vocab.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 49,
3
+ "[UNK]": 48,
4
+ "|": 0,
5
+ "γ„±": 1,
6
+ "γ„²": 2,
7
+ "γ„΄": 3,
8
+ "γ„΅": 4,
9
+ "γ„Ά": 5,
10
+ "γ„·": 6,
11
+ "γ„Έ": 7,
12
+ "γ„Ή": 8,
13
+ "γ„Ί": 9,
14
+ "γ„»": 10,
15
+ "γ„Ό": 11,
16
+ "γ…€": 12,
17
+ "ㅁ": 13,
18
+ "γ…‚": 14,
19
+ "γ…ƒ": 15,
20
+ "γ…„": 16,
21
+ "γ……": 17,
22
+ "γ…†": 18,
23
+ "γ…‡": 19,
24
+ "γ…ˆ": 20,
25
+ "γ…‰": 21,
26
+ "γ…Š": 22,
27
+ "γ…‹": 23,
28
+ "γ…Œ": 24,
29
+ "ㅍ": 25,
30
+ "γ…Ž": 26,
31
+ "ㅏ": 27,
32
+ "ㅐ": 28,
33
+ "γ…‘": 29,
34
+ "γ…’": 30,
35
+ "γ…“": 31,
36
+ "γ…”": 32,
37
+ "γ…•": 33,
38
+ "γ…–": 34,
39
+ "γ…—": 35,
40
+ "γ…˜": 36,
41
+ "γ…™": 37,
42
+ "γ…š": 38,
43
+ "γ…›": 39,
44
+ "γ…œ": 40,
45
+ "ㅝ": 41,
46
+ "γ…ž": 42,
47
+ "γ…Ÿ": 43,
48
+ "γ… ": 44,
49
+ "γ…‘": 45,
50
+ "γ…’": 46,
51
+ "γ…£": 47
52
+ }