Hugging Face's logo

yoon1000
/
ft_0123_korean_1

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2
Generated from Trainer
Model card Files
xet
 Community
yoon1000 commited on
Commit
8b87b6c
·
verified ·
1 Parent(s): 2afe90f

End of training

Browse files
Files changed (2) hide show
  1. README.md +149 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: ft_0123_korean_1
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # ft_0123_korean_1
15
+
16
+ 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.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.7160
19
+ - Cer: 0.1832
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_steps: 1000
45
+ - num_epochs: 8
46
+ - mixed_precision_training: Native AMP
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
51
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
52
+ | 60.2779 | 0.09 | 100 | 120.0675 | 0.9556 |
53
+ | 45.2315 | 0.18 | 200 | 66.7612 | 1.0 |
54
+ | 30.7852 | 0.27 | 300 | 50.1041 | 1.0 |
55
+ | 22.2754 | 0.35 | 400 | 31.5537 | 1.0 |
56
+ | 13.4785 | 0.44 | 500 | 13.3387 | 1.0 |
57
+ | 6.4901 | 0.53 | 600 | 5.4424 | 1.0 |
58
+ | 4.8734 | 0.62 | 700 | 5.0449 | 1.0 |
59
+ | 4.7501 | 0.71 | 800 | 4.9923 | 1.0 |
60
+ | 4.7477 | 0.8 | 900 | 4.9037 | 1.0 |
61
+ | 4.7511 | 0.88 | 1000 | 4.9181 | 1.0 |
62
+ | 4.7076 | 0.97 | 1100 | 4.8488 | 1.0 |
63
+ | 4.6829 | 1.06 | 1200 | 4.7397 | 1.0 |
64
+ | 4.6768 | 1.15 | 1300 | 4.7180 | 1.0 |
65
+ | 4.6089 | 1.24 | 1400 | 4.6611 | 1.0 |
66
+ | 4.56 | 1.33 | 1500 | 4.6175 | 1.0 |
67
+ | 4.499 | 1.41 | 1600 | 4.5056 | 0.9999 |
68
+ | 4.38 | 1.5 | 1700 | 4.2237 | 0.9857 |
69
+ | 4.1179 | 1.59 | 1800 | 3.8646 | 0.9816 |
70
+ | 3.7534 | 1.68 | 1900 | 3.2313 | 0.6453 |
71
+ | 3.3149 | 1.77 | 2000 | 2.8237 | 0.5349 |
72
+ | 3.0137 | 1.86 | 2100 | 2.5717 | 0.5091 |
73
+ | 2.8094 | 1.94 | 2200 | 2.3614 | 0.4624 |
74
+ | 2.5519 | 2.03 | 2300 | 2.2160 | 0.4501 |
75
+ | 2.4768 | 2.12 | 2400 | 2.0897 | 0.4274 |
76
+ | 2.3625 | 2.21 | 2500 | 1.9856 | 0.4168 |
77
+ | 2.2876 | 2.3 | 2600 | 1.9065 | 0.4016 |
78
+ | 2.2289 | 2.39 | 2700 | 1.8137 | 0.3930 |
79
+ | 2.0996 | 2.47 | 2800 | 1.7548 | 0.3755 |
80
+ | 2.0683 | 2.56 | 2900 | 1.6713 | 0.3590 |
81
+ | 2.0371 | 2.65 | 3000 | 1.6082 | 0.3528 |
82
+ | 1.8858 | 2.74 | 3100 | 1.5596 | 0.3453 |
83
+ | 1.8692 | 2.83 | 3200 | 1.5088 | 0.3346 |
84
+ | 1.8373 | 2.92 | 3300 | 1.4700 | 0.3299 |
85
+ | 1.8318 | 3.0 | 3400 | 1.4286 | 0.3208 |
86
+ | 1.7482 | 3.09 | 3500 | 1.4024 | 0.3151 |
87
+ | 1.6887 | 3.18 | 3600 | 1.3581 | 0.3126 |
88
+ | 1.6574 | 3.27 | 3700 | 1.3161 | 0.2998 |
89
+ | 1.6119 | 3.36 | 3800 | 1.2720 | 0.2924 |
90
+ | 1.6103 | 3.45 | 3900 | 1.2531 | 0.2921 |
91
+ | 1.5362 | 3.53 | 4000 | 1.2326 | 0.2917 |
92
+ | 1.4972 | 3.62 | 4100 | 1.1904 | 0.2816 |
93
+ | 1.5005 | 3.71 | 4200 | 1.1757 | 0.2784 |
94
+ | 1.4586 | 3.8 | 4300 | 1.1463 | 0.2737 |
95
+ | 1.4483 | 3.89 | 4400 | 1.1246 | 0.2694 |
96
+ | 1.4354 | 3.98 | 4500 | 1.0976 | 0.2641 |
97
+ | 1.3648 | 4.06 | 4600 | 1.0730 | 0.2606 |
98
+ | 1.3194 | 4.15 | 4700 | 1.0460 | 0.2579 |
99
+ | 1.3316 | 4.24 | 4800 | 1.0362 | 0.2516 |
100
+ | 1.3138 | 4.33 | 4900 | 1.0166 | 0.2475 |
101
+ | 1.3217 | 4.42 | 5000 | 0.9917 | 0.2456 |
102
+ | 1.2914 | 4.51 | 5100 | 0.9835 | 0.2411 |
103
+ | 1.2364 | 4.59 | 5200 | 0.9647 | 0.2409 |
104
+ | 1.2034 | 4.68 | 5300 | 0.9621 | 0.2368 |
105
+ | 1.2028 | 4.77 | 5400 | 0.9255 | 0.2311 |
106
+ | 1.2354 | 4.86 | 5500 | 0.9119 | 0.2280 |
107
+ | 1.2295 | 4.95 | 5600 | 0.9113 | 0.2287 |
108
+ | 1.2007 | 5.04 | 5700 | 0.8934 | 0.2229 |
109
+ | 1.1637 | 5.12 | 5800 | 0.8867 | 0.2256 |
110
+ | 1.1221 | 5.21 | 5900 | 0.8787 | 0.2213 |
111
+ | 1.171 | 5.3 | 6000 | 0.8607 | 0.2176 |
112
+ | 1.1042 | 5.39 | 6100 | 0.8514 | 0.2171 |
113
+ | 1.063 | 5.48 | 6200 | 0.8510 | 0.2175 |
114
+ | 1.0965 | 5.57 | 6300 | 0.8355 | 0.2107 |
115
+ | 1.0611 | 5.65 | 6400 | 0.8298 | 0.2096 |
116
+ | 1.0697 | 5.74 | 6500 | 0.8149 | 0.2074 |
117
+ | 1.0342 | 5.83 | 6600 | 0.8043 | 0.2037 |
118
+ | 1.0586 | 5.92 | 6700 | 0.8060 | 0.2028 |
119
+ | 1.0553 | 6.01 | 6800 | 0.8017 | 0.2029 |
120
+ | 1.0369 | 6.1 | 6900 | 0.7906 | 0.2015 |
121
+ | 0.9646 | 6.18 | 7000 | 0.7870 | 0.1987 |
122
+ | 0.9747 | 6.27 | 7100 | 0.7836 | 0.1970 |
123
+ | 0.9933 | 6.36 | 7200 | 0.7708 | 0.1963 |
124
+ | 0.9793 | 6.45 | 7300 | 0.7740 | 0.1957 |
125
+ | 0.9642 | 6.54 | 7400 | 0.7618 | 0.1934 |
126
+ | 0.9936 | 6.63 | 7500 | 0.7554 | 0.1919 |
127
+ | 0.9466 | 6.71 | 7600 | 0.7438 | 0.1891 |
128
+ | 0.9597 | 6.8 | 7700 | 0.7437 | 0.1900 |
129
+ | 0.9374 | 6.89 | 7800 | 0.7415 | 0.1909 |
130
+ | 0.9719 | 6.98 | 7900 | 0.7352 | 0.1908 |
131
+ | 0.9067 | 7.07 | 8000 | 0.7358 | 0.1880 |
132
+ | 0.8998 | 7.16 | 8100 | 0.7329 | 0.1879 |
133
+ | 0.9271 | 7.24 | 8200 | 0.7262 | 0.1864 |
134
+ | 0.8951 | 7.33 | 8300 | 0.7217 | 0.1860 |
135
+ | 0.9136 | 7.42 | 8400 | 0.7239 | 0.1854 |
136
+ | 0.9446 | 7.51 | 8500 | 0.7214 | 0.1844 |
137
+ | 0.8978 | 7.6 | 8600 | 0.7220 | 0.1837 |
138
+ | 0.8923 | 7.69 | 8700 | 0.7174 | 0.1838 |
139
+ | 0.9406 | 7.77 | 8800 | 0.7187 | 0.1836 |
140
+ | 0.9242 | 7.86 | 8900 | 0.7159 | 0.1836 |
141
+ | 0.8994 | 7.95 | 9000 | 0.7160 | 0.1832 |
142
+
143
+
144
+ ### Framework versions
145
+
146
+ - Transformers 4.36.2
147
+ - Pytorch 2.1.2+cu118
148
+ - Datasets 2.16.1
149
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b1bf9978629e025b9e084afda437e9feb1b9f193868f2f223dafb5a25359c5a
3
  size 1267317896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1cd8d8fe49d0d6b3c5348a73cb6ad086f8d2c9dd271cdc21767e19d07a62533
3
  size 1267317896