Hugging Face's logo

jaeyeon
/
korean-aihub-learning-3

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
1
jaeyeon commited on
Commit
dda9e1a
·
1 Parent(s): e80dac8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +160 -0
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: korean-aihub-learning-3
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
+ # korean-aihub-learning-3
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: 2.2854
18
+ - Wer: 0.7921
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: 0.0003
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 2
42
+ - total_train_batch_size: 8
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 500
46
+ - num_epochs: 100
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | No log | 0.99 | 35 | 45.5713 | 1.0 |
54
+ | No log | 1.99 | 70 | 24.4376 | 1.0 |
55
+ | 35.4145 | 2.99 | 105 | 18.3030 | 1.0 |
56
+ | 35.4145 | 3.99 | 140 | 12.6702 | 1.0 |
57
+ | 35.4145 | 4.99 | 175 | 7.4939 | 1.0 |
58
+ | 11.687 | 5.99 | 210 | 4.9592 | 1.0 |
59
+ | 11.687 | 6.99 | 245 | 4.6777 | 1.0 |
60
+ | 11.687 | 7.99 | 280 | 4.6597 | 1.0 |
61
+ | 4.8003 | 8.99 | 315 | 4.6777 | 1.0 |
62
+ | 4.8003 | 9.99 | 350 | 4.7003 | 1.0 |
63
+ | 4.8003 | 10.99 | 385 | 4.6129 | 1.0 |
64
+ | 4.6383 | 11.99 | 420 | 4.6209 | 1.0 |
65
+ | 4.6383 | 12.99 | 455 | 4.6035 | 1.0 |
66
+ | 4.6383 | 13.99 | 490 | 4.6166 | 1.0 |
67
+ | 4.577 | 14.99 | 525 | 4.6026 | 1.0 |
68
+ | 4.577 | 15.99 | 560 | 4.5337 | 1.0 |
69
+ | 4.577 | 16.99 | 595 | 4.5284 | 1.0 |
70
+ | 4.5124 | 17.99 | 630 | 4.5710 | 1.0 |
71
+ | 4.5124 | 18.99 | 665 | 4.5223 | 1.0 |
72
+ | 4.3818 | 19.99 | 700 | 4.4472 | 1.0 |
73
+ | 4.3818 | 20.99 | 735 | 4.4272 | 0.9977 |
74
+ | 4.3818 | 21.99 | 770 | 4.4160 | 0.9977 |
75
+ | 4.2796 | 22.99 | 805 | 4.3741 | 0.9988 |
76
+ | 4.2796 | 23.99 | 840 | 4.3087 | 1.0 |
77
+ | 4.2796 | 24.99 | 875 | 4.2336 | 1.0 |
78
+ | 4.0489 | 25.99 | 910 | 4.1352 | 0.9988 |
79
+ | 4.0489 | 26.99 | 945 | 4.0669 | 1.0 |
80
+ | 4.0489 | 27.99 | 980 | 3.8551 | 0.9988 |
81
+ | 3.6122 | 28.99 | 1015 | 3.6699 | 0.9919 |
82
+ | 3.6122 | 29.99 | 1050 | 3.4580 | 0.9781 |
83
+ | 3.6122 | 30.99 | 1085 | 3.1899 | 0.9434 |
84
+ | 2.8886 | 31.99 | 1120 | 3.0746 | 0.9550 |
85
+ | 2.8886 | 32.99 | 1155 | 2.8143 | 0.9353 |
86
+ | 2.8886 | 33.99 | 1190 | 2.7004 | 0.9122 |
87
+ | 2.0277 | 34.99 | 1225 | 2.5284 | 0.9076 |
88
+ | 2.0277 | 35.99 | 1260 | 2.4677 | 0.8972 |
89
+ | 2.0277 | 36.99 | 1295 | 2.3426 | 0.8568 |
90
+ | 1.2486 | 37.99 | 1330 | 2.2456 | 0.8822 |
91
+ | 1.2486 | 38.99 | 1365 | 2.3250 | 0.9238 |
92
+ | 0.7572 | 39.99 | 1400 | 2.2832 | 0.8557 |
93
+ | 0.7572 | 40.99 | 1435 | 2.2671 | 0.8406 |
94
+ | 0.7572 | 41.99 | 1470 | 2.3070 | 0.8857 |
95
+ | 0.4768 | 42.99 | 1505 | 2.2138 | 0.8476 |
96
+ | 0.4768 | 43.99 | 1540 | 2.2034 | 0.8799 |
97
+ | 0.4768 | 44.99 | 1575 | 2.2215 | 0.8487 |
98
+ | 0.3362 | 45.99 | 1610 | 2.3416 | 0.8834 |
99
+ | 0.3362 | 46.99 | 1645 | 2.3452 | 0.8383 |
100
+ | 0.3362 | 47.99 | 1680 | 2.2449 | 0.8360 |
101
+ | 0.257 | 48.99 | 1715 | 2.2249 | 0.8199 |
102
+ | 0.257 | 49.99 | 1750 | 2.3455 | 0.8106 |
103
+ | 0.257 | 50.99 | 1785 | 2.2537 | 0.8233 |
104
+ | 0.2116 | 51.99 | 1820 | 2.2501 | 0.8025 |
105
+ | 0.2116 | 52.99 | 1855 | 2.3180 | 0.8649 |
106
+ | 0.2116 | 53.99 | 1890 | 2.1855 | 0.8106 |
107
+ | 0.1787 | 54.99 | 1925 | 2.2140 | 0.8014 |
108
+ | 0.1787 | 55.99 | 1960 | 2.3140 | 0.8453 |
109
+ | 0.1787 | 56.99 | 1995 | 2.2140 | 0.8025 |
110
+ | 0.1498 | 57.99 | 2030 | 2.3381 | 0.8314 |
111
+ | 0.1498 | 58.99 | 2065 | 2.2591 | 0.8256 |
112
+ | 0.1372 | 59.99 | 2100 | 2.2538 | 0.7979 |
113
+ | 0.1372 | 60.99 | 2135 | 2.2052 | 0.7933 |
114
+ | 0.1372 | 61.99 | 2170 | 2.2370 | 0.8233 |
115
+ | 0.129 | 62.99 | 2205 | 2.2331 | 0.7898 |
116
+ | 0.129 | 63.99 | 2240 | 2.3022 | 0.8002 |
117
+ | 0.129 | 64.99 | 2275 | 2.3514 | 0.7956 |
118
+ | 0.1075 | 65.99 | 2310 | 2.3303 | 0.8279 |
119
+ | 0.1075 | 66.99 | 2345 | 2.2747 | 0.8025 |
120
+ | 0.1075 | 67.99 | 2380 | 2.2899 | 0.8152 |
121
+ | 0.0979 | 68.99 | 2415 | 2.3299 | 0.8164 |
122
+ | 0.0979 | 69.99 | 2450 | 2.1819 | 0.7945 |
123
+ | 0.0979 | 70.99 | 2485 | 2.2141 | 0.8222 |
124
+ | 0.0973 | 71.99 | 2520 | 2.3683 | 0.8395 |
125
+ | 0.0973 | 72.99 | 2555 | 2.2235 | 0.8199 |
126
+ | 0.0973 | 73.99 | 2590 | 2.2474 | 0.8048 |
127
+ | 0.0814 | 74.99 | 2625 | 2.3116 | 0.7968 |
128
+ | 0.0814 | 75.99 | 2660 | 2.2494 | 0.7945 |
129
+ | 0.0814 | 76.99 | 2695 | 2.2441 | 0.7968 |
130
+ | 0.0745 | 77.99 | 2730 | 2.2489 | 0.7864 |
131
+ | 0.0745 | 78.99 | 2765 | 2.2568 | 0.7921 |
132
+ | 0.0741 | 79.99 | 2800 | 2.2598 | 0.7875 |
133
+ | 0.0741 | 80.99 | 2835 | 2.3131 | 0.8002 |
134
+ | 0.0741 | 81.99 | 2870 | 2.2719 | 0.7898 |
135
+ | 0.0662 | 82.99 | 2905 | 2.2901 | 0.7875 |
136
+ | 0.0662 | 83.99 | 2940 | 2.3092 | 0.7979 |
137
+ | 0.0662 | 84.99 | 2975 | 2.3361 | 0.8048 |
138
+ | 0.0556 | 85.99 | 3010 | 2.3308 | 0.8152 |
139
+ | 0.0556 | 86.99 | 3045 | 2.3106 | 0.8164 |
140
+ | 0.0556 | 87.99 | 3080 | 2.3363 | 0.8002 |
141
+ | 0.0504 | 88.99 | 3115 | 2.3588 | 0.7910 |
142
+ | 0.0504 | 89.99 | 3150 | 2.3528 | 0.7956 |
143
+ | 0.0504 | 90.99 | 3185 | 2.3201 | 0.7794 |
144
+ | 0.0496 | 91.99 | 3220 | 2.3386 | 0.7991 |
145
+ | 0.0496 | 92.99 | 3255 | 2.3423 | 0.7956 |
146
+ | 0.0496 | 93.99 | 3290 | 2.3312 | 0.7956 |
147
+ | 0.0468 | 94.99 | 3325 | 2.3362 | 0.7968 |
148
+ | 0.0468 | 95.99 | 3360 | 2.2962 | 0.7887 |
149
+ | 0.0468 | 96.99 | 3395 | 2.2864 | 0.7841 |
150
+ | 0.0475 | 97.99 | 3430 | 2.2870 | 0.7898 |
151
+ | 0.0475 | 98.99 | 3465 | 2.2866 | 0.7898 |
152
+ | 0.0411 | 99.99 | 3500 | 2.2854 | 0.7921 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.20.1
158
+ - Pytorch 1.12.0+cu113
159
+ - Datasets 2.3.2
160
+ - Tokenizers 0.12.1