Yurii Paniv
commited on
Commit
•
2162892
1
Parent(s):
72470a2
Update model to WER 27.99%
Browse files- README.md +66 -140
- added_tokens.json +1 -1
- all_results.json +0 -15
- config.json +6 -5
- eval_results.json +0 -10
- preprocessor_config.json +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -1
- tokenizer_config.json +1 -1
- train_results.json +0 -8
- trainer_state.json +0 -0
- training_args.bin +1 -1
- vocab.json +1 -1
README.md
CHANGED
@@ -10,7 +10,7 @@ datasets:
|
|
10 |
- common_voice
|
11 |
model-index:
|
12 |
- name: wav2vec2-xls-r-300m-uk
|
13 |
-
|
14 |
- task:
|
15 |
name: Speech Recognition
|
16 |
type: automatic-speech-recognition
|
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Test WER
|
23 |
type: wer
|
24 |
-
value:
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -29,11 +29,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
29 |
|
30 |
# wav2vec2-xls-r-300m-uk
|
31 |
|
32 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Wer: 0.
|
36 |
-
- Cer: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,149 +52,75 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate: 0.
|
56 |
- train_batch_size: 8
|
57 |
-
- eval_batch_size:
|
58 |
- seed: 42
|
|
|
|
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
- lr_scheduler_warmup_steps: 500
|
62 |
-
- num_epochs:
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
-
| Training Loss | Epoch | Step
|
68 |
-
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
|
|
78 |
-
|
|
79 |
-
|
|
80 |
-
|
|
81 |
-
|
|
82 |
-
|
|
83 |
-
|
|
84 |
-
|
|
85 |
-
| 0.
|
86 |
-
|
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
119 |
-
| 0.
|
120 |
-
| 0.
|
121 |
-
| 0.
|
122 |
-
| 0.8164 | 6.59 | 27000 | 0.1653 | 0.5460 | 0.6329 |
|
123 |
-
| 0.755 | 6.71 | 27500 | 0.1694 | 0.5420 | 0.6614 |
|
124 |
-
| 0.822 | 6.83 | 28000 | 0.1699 | 0.5540 | 0.6493 |
|
125 |
-
| 0.7957 | 6.95 | 28500 | 0.1630 | 0.5358 | 0.6373 |
|
126 |
-
| 0.7739 | 7.08 | 29000 | 0.1727 | 0.5662 | 0.6696 |
|
127 |
-
| 0.7833 | 7.2 | 29500 | 0.1594 | 0.5323 | 0.6227 |
|
128 |
-
| 0.7737 | 7.32 | 30000 | 0.1613 | 0.5349 | 0.6303 |
|
129 |
-
| 0.7697 | 7.44 | 30500 | 0.1623 | 0.5315 | 0.6386 |
|
130 |
-
| 0.7647 | 7.56 | 31000 | 0.1608 | 0.5346 | 0.6219 |
|
131 |
-
| 0.7123 | 7.69 | 31500 | 0.1561 | 0.5195 | 0.6110 |
|
132 |
-
| 0.7412 | 7.81 | 32000 | 0.1613 | 0.5385 | 0.6256 |
|
133 |
-
| 0.7702 | 7.93 | 32500 | 0.1614 | 0.5291 | 0.6343 |
|
134 |
-
| 0.7561 | 8.05 | 33000 | 0.1553 | 0.5044 | 0.6138 |
|
135 |
-
| 0.6707 | 8.78 | 36000 | 0.1484 | 0.4949 | 0.5881 |
|
136 |
-
| 0.719 | 9.52 | 39000 | 0.1508 | 0.5014 | 0.5959 |
|
137 |
-
| 0.6563 | 10.25 | 42000 | 0.1442 | 0.4852 | 0.5691 |
|
138 |
-
| 0.7166 | 10.98 | 45000 | 0.1437 | 0.4731 | 0.5718 |
|
139 |
-
| 0.6627 | 11.71 | 48000 | 0.1421 | 0.4787 | 0.5595 |
|
140 |
-
| 0.6642 | 12.45 | 51000 | 0.1353 | 0.4787 | 0.5417 |
|
141 |
-
| 0.615 | 13.18 | 54000 | 0.1324 | 0.4704 | 0.5297 |
|
142 |
-
| 0.6308 | 13.91 | 57000 | 0.1298 | 0.4570 | 0.5181 |
|
143 |
-
| 0.6169 | 14.64 | 60000 | 0.1291 | 0.4514 | 0.5106 |
|
144 |
-
| 0.5731 | 15.37 | 63000 | 0.1259 | 0.4462 | 0.5028 |
|
145 |
-
| 0.5328 | 16.11 | 66000 | 0.1246 | 0.4535 | 0.5023 |
|
146 |
-
| 0.5743 | 16.84 | 69000 | 0.1255 | 0.4555 | 0.5069 |
|
147 |
-
| 0.5363 | 17.57 | 72000 | 0.1214 | 0.4389 | 0.4915 |
|
148 |
-
| 0.5078 | 18.3 | 75000 | 0.1222 | 0.4525 | 0.4915 |
|
149 |
-
| 0.5075 | 19.03 | 78000 | 0.1208 | 0.4532 | 0.4871 |
|
150 |
-
| 0.5461 | 19.77 | 81000 | 0.1196 | 0.4401 | 0.4813 |
|
151 |
-
| 0.5044 | 20.5 | 84000 | 0.1144 | 0.4268 | 0.4654 |
|
152 |
-
| 0.4332 | 21.23 | 87000 | 0.1138 | 0.4383 | 0.4626 |
|
153 |
-
| 0.4671 | 21.96 | 90000 | 0.1118 | 0.4198 | 0.4547 |
|
154 |
-
| 0.4451 | 22.69 | 93000 | 0.1119 | 0.4426 | 0.4509 |
|
155 |
-
| 0.4319 | 23.43 | 96000 | 0.1096 | 0.4272 | 0.4472 |
|
156 |
-
| 0.3624 | 24.16 | 99000 | 0.1078 | 0.4347 | 0.4437 |
|
157 |
-
| 0.4512 | 24.89 | 102000 | 0.1102 | 0.4271 | 0.4471 |
|
158 |
-
| 0.4049 | 25.62 | 105000 | 0.1071 | 0.4207 | 0.4349 |
|
159 |
-
| 0.4134 | 26.35 | 108000 | 0.1061 | 0.4302 | 0.4351 |
|
160 |
-
| 0.4083 | 27.09 | 111000 | 0.1062 | 0.4583 | 0.4320 |
|
161 |
-
| 0.4618 | 27.82 | 114000 | 0.1046 | 0.4229 | 0.4281 |
|
162 |
-
| 0.4538 | 28.55 | 117000 | 0.1022 | 0.4060 | 0.42 |
|
163 |
-
| 0.4378 | 29.28 | 120000 | 0.1030 | 0.4239 | 0.4161 |
|
164 |
-
| 0.4062 | 30.01 | 123000 | 0.1012 | 0.4130 | 0.4171 |
|
165 |
-
| 0.3903 | 30.75 | 126000 | 0.1006 | 0.4134 | 0.4124 |
|
166 |
-
| 0.369 | 31.48 | 129000 | 0.0976 | 0.4163 | 0.4007 |
|
167 |
-
| 0.3896 | 32.21 | 132000 | 0.0986 | 0.3985 | 0.4015 |
|
168 |
-
| 0.3912 | 32.94 | 135000 | 0.0964 | 0.4103 | 0.3948 |
|
169 |
-
| 0.3995 | 33.67 | 138000 | 0.0975 | 0.3962 | 0.4024 |
|
170 |
-
| 0.4042 | 34.41 | 141000 | 0.0940 | 0.4196 | 0.3947 |
|
171 |
-
| 0.4055 | 35.14 | 144000 | 0.0949 | 0.3956 | 0.3882 |
|
172 |
-
| 0.3831 | 35.87 | 147000 | 0.0933 | 0.3962 | 0.3842 |
|
173 |
-
| 0.408 | 36.6 | 150000 | 0.0914 | 0.4019 | 0.3781 |
|
174 |
-
| 0.3632 | 37.34 | 153000 | 0.0917 | 0.4083 | 0.3814 |
|
175 |
-
| 0.381 | 38.07 | 156000 | 0.0914 | 0.4063 | 0.3738 |
|
176 |
-
| 0.3891 | 38.8 | 159000 | 0.0900 | 0.4060 | 0.3734 |
|
177 |
-
| 0.3668 | 39.53 | 162000 | 0.0893 | 0.4087 | 0.3701 |
|
178 |
-
| 0.3243 | 133.39 | 165000 | 0.3808 | 0.3460 | 0.0820 |
|
179 |
-
| 0.2861 | 135.81 | 168000 | 0.3986 | 0.3321 | 0.0788 |
|
180 |
-
| 0.2684 | 138.24 | 171000 | 0.4015 | 0.3299 | 0.0774 |
|
181 |
-
| 0.3027 | 140.66 | 174000 | 0.4023 | 0.3272 | 0.0771 |
|
182 |
-
| 0.2742 | 143.09 | 177000 | 0.4133 | 0.3273 | 0.0770 |
|
183 |
-
| 0.2339 | 145.51 | 180000 | 0.4287 | 0.3268 | 0.0771 |
|
184 |
-
| 0.2547 | 147.94 | 183000 | 0.4396 | 0.3254 | 0.0768 |
|
185 |
-
| 0.2072 | 150.36 | 186000 | 0.4586 | 0.3289 | 0.0774 |
|
186 |
-
| 0.2444 | 152.79 | 189000 | 0.4524 | 0.3239 | 0.0762 |
|
187 |
-
| 0.2272 | 155.21 | 192000 | 0.4620 | 0.3222 | 0.0759 |
|
188 |
-
| 0.2102 | 157.64 | 195000 | 0.4533 | 0.3212 | 0.0754 |
|
189 |
-
| 0.2231 | 160.06 | 198000 | 0.4563 | 0.3183 | 0.0745 |
|
190 |
-
| 0.2096 | 162.49 | 201000 | 0.4669 | 0.3183 | 0.0747 |
|
191 |
-
| 0.2173 | 164.92 | 204000 | 0.4704 | 0.3180 | 0.0746 |
|
192 |
-
| 0.1797 | 167.34 | 207000 | 0.4653 | 0.3169 | 0.0739 |
|
193 |
-
| 0.1841 | 169.77 | 210000 | 0.4726 | 0.3164 | 0.0737 |
|
194 |
-
| 0.1774 | 172.19 | 213000 | 0.4742 | 0.3162 | 0.0738 |
|
195 |
-
| 0.1819 | 174.62 | 216000 | 0.4720 | 0.3149 | 0.0737 |
|
196 |
-
| 0.1746 | 177.04 | 219000 | 0.4736 | 0.3153 | 0.0738 |
|
197 |
-
| 0.2101 | 179.47 | 222000 | 0.4756 | 0.3161 | 0.0738 |
|
198 |
|
199 |
|
200 |
### Framework versions
|
|
|
10 |
- common_voice
|
11 |
model-index:
|
12 |
- name: wav2vec2-xls-r-300m-uk
|
13 |
+
results:
|
14 |
- task:
|
15 |
name: Speech Recognition
|
16 |
type: automatic-speech-recognition
|
|
|
21 |
metrics:
|
22 |
- name: Test WER
|
23 |
type: wer
|
24 |
+
value: 27.99
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
# wav2vec2-xls-r-300m-uk
|
31 |
|
32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.4165
|
35 |
+
- Wer: 0.2799
|
36 |
+
- Cer: 0.0601
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0003
|
56 |
- train_batch_size: 8
|
57 |
+
- eval_batch_size: 8
|
58 |
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 20
|
60 |
+
- total_train_batch_size: 160
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
- lr_scheduler_type: linear
|
63 |
- lr_scheduler_warmup_steps: 500
|
64 |
+
- num_epochs: 500
|
65 |
- mixed_precision_training: Native AMP
|
66 |
|
67 |
### Training results
|
68 |
|
69 |
+
| Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
|
70 |
+
|:-------------:|:------:|:-----:|:------:|:---------------:|:------:|
|
71 |
+
| 4.3982 | 9.3 | 400 | 0.1437 | 0.5218 | 0.6507 |
|
72 |
+
| 0.229 | 18.6 | 800 | 0.0848 | 0.3679 | 0.4048 |
|
73 |
+
| 0.1054 | 27.9 | 1200 | 0.0778 | 0.3813 | 0.3670 |
|
74 |
+
| 0.0784 | 37.21 | 1600 | 0.0747 | 0.3839 | 0.3550 |
|
75 |
+
| 0.066 | 46.51 | 2000 | 0.0736 | 0.3970 | 0.3443 |
|
76 |
+
| 0.0603 | 55.8 | 2400 | 0.0722 | 0.3702 | 0.3393 |
|
77 |
+
| 0.0539 | 65.11 | 2800 | 0.0724 | 0.3762 | 0.3388 |
|
78 |
+
| 0.0497 | 74.41 | 3200 | 0.0713 | 0.3623 | 0.3414 |
|
79 |
+
| 0.0432 | 83.71 | 3600 | 0.0725 | 0.3847 | 0.3346 |
|
80 |
+
| 0.0438 | 93.02 | 4000 | 0.0750 | 0.4058 | 0.3393 |
|
81 |
+
| 0.0413 | 102.32 | 4400 | 0.0727 | 0.3957 | 0.3363 |
|
82 |
+
| 0.039 | 111.62 | 4800 | 0.0718 | 0.3865 | 0.3330 |
|
83 |
+
| 0.0356 | 120.92 | 5200 | 0.0711 | 0.3860 | 0.3319 |
|
84 |
+
| 0.0336 | 130.23 | 5600 | 0.0700 | 0.3902 | 0.3242 |
|
85 |
+
| 0.034 | 139.53 | 6000 | 0.0732 | 0.3930 | 0.3337 |
|
86 |
+
| 0.0273 | 148.83 | 6400 | 0.0748 | 0.3912 | 0.3375 |
|
87 |
+
| 0.027 | 158.14 | 6800 | 0.0752 | 0.4266 | 0.3434 |
|
88 |
+
| 0.028 | 167.44 | 7200 | 0.0708 | 0.3895 | 0.3227 |
|
89 |
+
| 0.0241 | 176.73 | 7600 | 0.0727 | 0.3967 | 0.3294 |
|
90 |
+
| 0.0241 | 186.05 | 8000 | 0.0712 | 0.4058 | 0.3255 |
|
91 |
+
| 0.0209 | 195.34 | 8400 | 0.0702 | 0.4102 | 0.3233 |
|
92 |
+
| 0.0206 | 204.64 | 8800 | 0.0699 | 0.4075 | 0.3194 |
|
93 |
+
| 0.0172 | 213.94 | 9200 | 0.0695 | 0.4222 | 0.3191 |
|
94 |
+
| 0.0166 | 223.25 | 9600 | 0.0678 | 0.3860 | 0.3135 |
|
95 |
+
| 0.0156 | 232.55 | 10000 | 0.0677 | 0.4035 | 0.3117 |
|
96 |
+
| 0.0149 | 241.85 | 10400 | 0.0677 | 0.3951 | 0.3087 |
|
97 |
+
| 0.0142 | 251.16 | 10800 | 0.0674 | 0.3972 | 0.3097 |
|
98 |
+
| 0.0134 | 260.46 | 11200 | 0.0675 | 0.4069 | 0.3111 |
|
99 |
+
| 0.0116 | 269.76 | 11600 | 0.0697 | 0.4189 | 0.3161 |
|
100 |
+
| 0.0119 | 279.07 | 12000 | 0.0648 | 0.3902 | 0.3008 |
|
101 |
+
| 0.0098 | 288.37 | 12400 | 0.0652 | 0.4095 | 0.3002 |
|
102 |
+
| 0.0091 | 297.67 | 12800 | 0.0644 | 0.3892 | 0.2990 |
|
103 |
+
| 0.0094 | 306.96 | 13200 | 0.0647 | 0.4026 | 0.2983 |
|
104 |
+
| 0.0081 | 316.28 | 13600 | 0.0646 | 0.4303 | 0.2978 |
|
105 |
+
| 0.0079 | 325.57 | 14000 | 0.0643 | 0.4044 | 0.2980 |
|
106 |
+
| 0.0072 | 334.87 | 14400 | 0.0655 | 0.3828 | 0.2999 |
|
107 |
+
| 0.0081 | 344.18 | 14800 | 0.0668 | 0.4108 | 0.3046 |
|
108 |
+
| 0.0088 | 353.48 | 15200 | 0.0654 | 0.4019 | 0.2993 |
|
109 |
+
| 0.0088 | 362.78 | 15600 | 0.0681 | 0.4073 | 0.3091 |
|
110 |
+
| 0.0079 | 372.09 | 16000 | 0.0667 | 0.4204 | 0.3055 |
|
111 |
+
| 0.0072 | 381.39 | 16400 | 0.0656 | 0.4030 | 0.3028 |
|
112 |
+
| 0.0073 | 390.69 | 16800 | 0.0677 | 0.4032 | 0.3081 |
|
113 |
+
| 0.0069 | 399.99 | 17200 | 0.0669 | 0.4130 | 0.3021 |
|
114 |
+
| 0.0063 | 409.3 | 17600 | 0.0651 | 0.4072 | 0.2979 |
|
115 |
+
| 0.0059 | 418.6 | 18000 | 0.0640 | 0.4110 | 0.2969 |
|
116 |
+
| 0.0056 | 427.9 | 18400 | 0.0647 | 0.4229 | 0.2995 |
|
117 |
+
| 0.005 | 437.21 | 18800 | 0.0624 | 0.4118 | 0.2885 |
|
118 |
+
| 0.0046 | 446.51 | 19200 | 0.0615 | 0.4111 | 0.2841 |
|
119 |
+
| 0.0043 | 455.8 | 19600 | 0.0616 | 0.4071 | 0.2850 |
|
120 |
+
| 0.0038 | 465.11 | 20000 | 0.0624 | 0.4268 | 0.2867 |
|
121 |
+
| 0.0035 | 474.41 | 20400 | 0.0605 | 0.4117 | 0.2820 |
|
122 |
+
| 0.0035 | 483.71 | 20800 | 0.0602 | 0.4155 | 0.2819 |
|
123 |
+
| 0.0034 | 493.02 | 21200 | 0.0601 | 0.4165 | 0.2799 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
|
125 |
|
126 |
### Framework versions
|
added_tokens.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"<s>":
|
|
|
1 |
+
{"<s>": 36, "</s>": 37}
|
all_results.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 180.0,
|
3 |
-
"eval_cer": 0.07386836134410645,
|
4 |
-
"eval_loss": 0.4753616452217102,
|
5 |
-
"eval_runtime": 157.9734,
|
6 |
-
"eval_samples": 4193,
|
7 |
-
"eval_samples_per_second": 26.542,
|
8 |
-
"eval_steps_per_second": 6.64,
|
9 |
-
"eval_wer": 0.31588907014681894,
|
10 |
-
"train_loss": 0.061750437557927515,
|
11 |
-
"train_runtime": 29496.4676,
|
12 |
-
"train_samples": 9889,
|
13 |
-
"train_samples_per_second": 60.347,
|
14 |
-
"train_steps_per_second": 7.549
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -52,6 +52,7 @@
|
|
52 |
"feat_proj_dropout": 0.0,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
"final_dropout": 0.0,
|
|
|
55 |
"hidden_act": "gelu",
|
56 |
"hidden_dropout": 0.0,
|
57 |
"hidden_size": 1024,
|
@@ -59,12 +60,12 @@
|
|
59 |
"intermediate_size": 4096,
|
60 |
"layer_norm_eps": 1e-05,
|
61 |
"layerdrop": 0.0,
|
62 |
-
"mask_feature_length":
|
63 |
"mask_feature_min_masks": 0,
|
64 |
-
"mask_feature_prob": 0.
|
65 |
"mask_time_length": 10,
|
66 |
"mask_time_min_masks": 2,
|
67 |
-
"mask_time_prob": 0.
|
68 |
"model_type": "wav2vec2",
|
69 |
"num_adapter_layers": 3,
|
70 |
"num_attention_heads": 16,
|
@@ -76,10 +77,10 @@
|
|
76 |
"num_hidden_layers": 24,
|
77 |
"num_negatives": 100,
|
78 |
"output_hidden_size": 1024,
|
79 |
-
"pad_token_id":
|
80 |
"proj_codevector_dim": 768,
|
81 |
"torch_dtype": "float32",
|
82 |
"transformers_version": "4.14.1",
|
83 |
"use_weighted_layer_sum": false,
|
84 |
-
"vocab_size":
|
85 |
}
|
|
|
52 |
"feat_proj_dropout": 0.0,
|
53 |
"feat_quantizer_dropout": 0.0,
|
54 |
"final_dropout": 0.0,
|
55 |
+
"gradient_checkpointing": false,
|
56 |
"hidden_act": "gelu",
|
57 |
"hidden_dropout": 0.0,
|
58 |
"hidden_size": 1024,
|
|
|
60 |
"intermediate_size": 4096,
|
61 |
"layer_norm_eps": 1e-05,
|
62 |
"layerdrop": 0.0,
|
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": 0.05,
|
69 |
"model_type": "wav2vec2",
|
70 |
"num_adapter_layers": 3,
|
71 |
"num_attention_heads": 16,
|
|
|
77 |
"num_hidden_layers": 24,
|
78 |
"num_negatives": 100,
|
79 |
"output_hidden_size": 1024,
|
80 |
+
"pad_token_id": 35,
|
81 |
"proj_codevector_dim": 768,
|
82 |
"torch_dtype": "float32",
|
83 |
"transformers_version": "4.14.1",
|
84 |
"use_weighted_layer_sum": false,
|
85 |
+
"vocab_size": 38
|
86 |
}
|
eval_results.json
DELETED
@@ -1,10 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 180.0,
|
3 |
-
"eval_cer": 0.07386836134410645,
|
4 |
-
"eval_loss": 0.4753616452217102,
|
5 |
-
"eval_runtime": 157.9734,
|
6 |
-
"eval_samples": 4193,
|
7 |
-
"eval_samples_per_second": 26.542,
|
8 |
-
"eval_steps_per_second": 6.64,
|
9 |
-
"eval_wer": 0.31588907014681894
|
10 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
preprocessor_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
-
"padding_value": 0,
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
|
|
3 |
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
"feature_size": 1,
|
5 |
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
"return_attention_mask": true,
|
8 |
"sampling_rate": 16000
|
9 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d59ff36212cbdd264b1851e4e7f8ebc8f3108665363c9ed12efdd9f2754c7337
|
3 |
+
size 1262079473
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./
|
|
|
1 |
+
{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
|
train_results.json
DELETED
@@ -1,8 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"epoch": 180.0,
|
3 |
-
"train_loss": 0.061750437557927515,
|
4 |
-
"train_runtime": 29496.4676,
|
5 |
-
"train_samples": 9889,
|
6 |
-
"train_samples_per_second": 60.347,
|
7 |
-
"train_steps_per_second": 7.549
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2927
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a9f2d55e2d30c3efb297191f66a757c1a52ea11bcbc472646289172e2a0d182
|
3 |
size 2927
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"а": 1, "б": 2, "в": 3, "г": 4, "д": 5, "е": 6, "ж": 7, "з": 8, "и": 9, "й": 10, "к": 11, "л": 12, "м": 13, "н": 14, "о": 15, "п": 16, "р": 17, "с": 18, "т": 19, "у": 20, "ф": 21, "х": 22, "ц": 23, "ч": 24, "ш": 25, "щ": 26, "ь": 27, "ю": 28, "я": 29, "є": 30, "і": 31, "ї": 32, "ґ": 33, "|": 0, "[UNK]": 34, "[PAD]": 35}
|