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
275e6bc
·
1 Parent(s): d7c415d

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: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram
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
+ # ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram
14
+
15
+ This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.4814
18
+ - Wer: 0.1994
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: 5e-05
38
+ - train_batch_size: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 64
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 100
46
+ - num_epochs: 100.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
53
+ | 0.3993 | 1.0 | 72 | 0.5761 | 0.2678 |
54
+ | 0.4252 | 2.0 | 144 | 0.5669 | 0.2987 |
55
+ | 0.4309 | 3.0 | 216 | 0.5532 | 0.2914 |
56
+ | 0.4151 | 4.0 | 288 | 0.5907 | 0.2773 |
57
+ | 0.4229 | 5.0 | 360 | 0.5353 | 0.2502 |
58
+ | 0.4229 | 6.0 | 432 | 0.5442 | 0.2607 |
59
+ | 0.4106 | 7.0 | 504 | 0.5387 | 0.2513 |
60
+ | 0.4161 | 8.0 | 576 | 0.5407 | 0.2592 |
61
+ | 0.4072 | 9.0 | 648 | 0.5012 | 0.2493 |
62
+ | 0.4301 | 10.0 | 720 | 0.5449 | 0.2542 |
63
+ | 0.419 | 11.0 | 792 | 0.5025 | 0.2558 |
64
+ | 0.4336 | 12.0 | 864 | 0.5267 | 0.2451 |
65
+ | 0.4188 | 13.0 | 936 | 0.5068 | 0.2582 |
66
+ | 0.4005 | 14.0 | 1008 | 0.5392 | 0.2529 |
67
+ | 0.4213 | 15.0 | 1080 | 0.5083 | 0.2492 |
68
+ | 0.4123 | 16.0 | 1152 | 0.4909 | 0.2481 |
69
+ | 0.3854 | 17.0 | 1224 | 0.5270 | 0.2593 |
70
+ | 0.3887 | 18.0 | 1296 | 0.5059 | 0.2503 |
71
+ | 0.3934 | 19.0 | 1368 | 0.4929 | 0.2353 |
72
+ | 0.4005 | 20.0 | 1440 | 0.5170 | 0.2444 |
73
+ | 0.4018 | 21.0 | 1512 | 0.4931 | 0.2406 |
74
+ | 0.3981 | 22.0 | 1584 | 0.4988 | 0.2345 |
75
+ | 0.3645 | 23.0 | 1656 | 0.5221 | 0.2495 |
76
+ | 0.3727 | 24.0 | 1728 | 0.5192 | 0.2361 |
77
+ | 0.3751 | 25.0 | 1800 | 0.4996 | 0.2403 |
78
+ | 0.3839 | 26.0 | 1872 | 0.4840 | 0.2227 |
79
+ | 0.3739 | 27.0 | 1944 | 0.4790 | 0.2265 |
80
+ | 0.3781 | 28.0 | 2016 | 0.5081 | 0.2247 |
81
+ | 0.3655 | 29.0 | 2088 | 0.4903 | 0.2263 |
82
+ | 0.3832 | 30.0 | 2160 | 0.5196 | 0.2383 |
83
+ | 0.3662 | 31.0 | 2232 | 0.5286 | 0.2363 |
84
+ | 0.3692 | 32.0 | 2304 | 0.5283 | 0.2460 |
85
+ | 0.3484 | 33.0 | 2376 | 0.4906 | 0.2267 |
86
+ | 0.3493 | 34.0 | 2448 | 0.4983 | 0.2214 |
87
+ | 0.3783 | 35.0 | 2520 | 0.5359 | 0.2319 |
88
+ | 0.3604 | 36.0 | 2592 | 0.5129 | 0.2371 |
89
+ | 0.3796 | 37.0 | 2664 | 0.4994 | 0.2320 |
90
+ | 0.3629 | 38.0 | 2736 | 0.4726 | 0.2226 |
91
+ | 0.3428 | 39.0 | 2808 | 0.5130 | 0.2225 |
92
+ | 0.375 | 40.0 | 2880 | 0.5155 | 0.2285 |
93
+ | 0.3581 | 41.0 | 2952 | 0.4994 | 0.2267 |
94
+ | 0.3394 | 42.0 | 3024 | 0.4989 | 0.2177 |
95
+ | 0.3421 | 43.0 | 3096 | 0.4820 | 0.2274 |
96
+ | 0.342 | 44.0 | 3168 | 0.4839 | 0.2189 |
97
+ | 0.3482 | 45.0 | 3240 | 0.4979 | 0.2120 |
98
+ | 0.3494 | 46.0 | 3312 | 0.5069 | 0.2186 |
99
+ | 0.345 | 47.0 | 3384 | 0.4998 | 0.2321 |
100
+ | 0.327 | 48.0 | 3456 | 0.4978 | 0.2189 |
101
+ | 0.3266 | 49.0 | 3528 | 0.5079 | 0.2187 |
102
+ | 0.3353 | 50.0 | 3600 | 0.5302 | 0.2235 |
103
+ | 0.3384 | 51.0 | 3672 | 0.4838 | 0.2117 |
104
+ | 0.3259 | 52.0 | 3744 | 0.5022 | 0.2169 |
105
+ | 0.336 | 53.0 | 3816 | 0.4834 | 0.2214 |
106
+ | 0.3123 | 54.0 | 3888 | 0.5113 | 0.2164 |
107
+ | 0.3306 | 55.0 | 3960 | 0.4770 | 0.2112 |
108
+ | 0.3344 | 56.0 | 4032 | 0.4752 | 0.2130 |
109
+ | 0.3279 | 57.0 | 4104 | 0.4953 | 0.2123 |
110
+ | 0.3067 | 58.0 | 4176 | 0.4823 | 0.2175 |
111
+ | 0.3131 | 59.0 | 4248 | 0.4857 | 0.2137 |
112
+ | 0.3178 | 60.0 | 4320 | 0.4969 | 0.2154 |
113
+ | 0.3306 | 61.0 | 4392 | 0.4816 | 0.2166 |
114
+ | 0.3152 | 62.0 | 4464 | 0.4695 | 0.2106 |
115
+ | 0.3119 | 63.0 | 4536 | 0.5111 | 0.2106 |
116
+ | 0.3124 | 64.0 | 4608 | 0.5017 | 0.2119 |
117
+ | 0.317 | 65.0 | 4680 | 0.5071 | 0.2165 |
118
+ | 0.2934 | 66.0 | 4752 | 0.4819 | 0.2168 |
119
+ | 0.3103 | 67.0 | 4824 | 0.4944 | 0.2143 |
120
+ | 0.3078 | 68.0 | 4896 | 0.5004 | 0.2110 |
121
+ | 0.3084 | 69.0 | 4968 | 0.4998 | 0.2148 |
122
+ | 0.3147 | 70.0 | 5040 | 0.4885 | 0.2099 |
123
+ | 0.3081 | 71.0 | 5112 | 0.5062 | 0.2096 |
124
+ | 0.3046 | 72.0 | 5184 | 0.4790 | 0.2124 |
125
+ | 0.2993 | 73.0 | 5256 | 0.5045 | 0.2096 |
126
+ | 0.2844 | 74.0 | 5328 | 0.4865 | 0.2060 |
127
+ | 0.3061 | 75.0 | 5400 | 0.4997 | 0.2103 |
128
+ | 0.305 | 76.0 | 5472 | 0.5118 | 0.2120 |
129
+ | 0.3015 | 77.0 | 5544 | 0.4900 | 0.2096 |
130
+ | 0.2969 | 78.0 | 5616 | 0.4984 | 0.2106 |
131
+ | 0.2988 | 79.0 | 5688 | 0.4948 | 0.2065 |
132
+ | 0.3006 | 80.0 | 5760 | 0.4850 | 0.2032 |
133
+ | 0.2982 | 81.0 | 5832 | 0.4933 | 0.2047 |
134
+ | 0.2938 | 82.0 | 5904 | 0.4997 | 0.2052 |
135
+ | 0.2903 | 83.0 | 5976 | 0.4919 | 0.2034 |
136
+ | 0.297 | 84.0 | 6048 | 0.4807 | 0.2026 |
137
+ | 0.2955 | 85.0 | 6120 | 0.4953 | 0.2048 |
138
+ | 0.2847 | 86.0 | 6192 | 0.4951 | 0.2022 |
139
+ | 0.2891 | 87.0 | 6264 | 0.4942 | 0.2036 |
140
+ | 0.2895 | 88.0 | 6336 | 0.4888 | 0.2020 |
141
+ | 0.2823 | 89.0 | 6408 | 0.4968 | 0.2033 |
142
+ | 0.2885 | 90.0 | 6480 | 0.5042 | 0.2040 |
143
+ | 0.2876 | 91.0 | 6552 | 0.4943 | 0.2025 |
144
+ | 0.2765 | 92.0 | 6624 | 0.4961 | 0.2004 |
145
+ | 0.282 | 93.0 | 6696 | 0.4847 | 0.2017 |
146
+ | 0.277 | 94.0 | 6768 | 0.4849 | 0.1994 |
147
+ | 0.2883 | 95.0 | 6840 | 0.4849 | 0.2003 |
148
+ | 0.2906 | 96.0 | 6912 | 0.4912 | 0.2002 |
149
+ | 0.2781 | 97.0 | 6984 | 0.4874 | 0.2016 |
150
+ | 0.2836 | 98.0 | 7056 | 0.4825 | 0.1996 |
151
+ | 0.2676 | 99.0 | 7128 | 0.4806 | 0.1995 |
152
+ | 0.28 | 100.0 | 7200 | 0.4814 | 0.1994 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.21.0.dev0
158
+ - Pytorch 1.9.1+cu102
159
+ - Datasets 2.3.3.dev0
160
+ - Tokenizers 0.12.1