Hugging Face's logo

gary109
/
ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v2

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
1f4062f
•
1 Parent(s): 9ecbcbf

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +176 -0
README.md ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - ai_light_dance
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v2
10
+ results:
11
+ - task:
12
+ name: Automatic Speech Recognition
13
+ type: automatic-speech-recognition
14
+ dataset:
15
+ name: ai_light_dance
16
+ type: ai_light_dance
17
+ config: onset-idmt-smt-drums-v2+MDBDrums
18
+ split: train
19
+ args: onset-idmt-smt-drums-v2+MDBDrums
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 0.3098927294398093
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v2
30
+
31
+ This model is a fine-tuned version of [gary109/ai-light-dance_drums_pretrain_wav2vec2-base-new](https://huggingface.co/gary109/ai-light-dance_drums_pretrain_wav2vec2-base-new) on the ai_light_dance dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.5744
34
+ - Wer: 0.3099
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0004
54
+ - train_batch_size: 4
55
+ - eval_batch_size: 4
56
+ - seed: 42
57
+ - gradient_accumulation_steps: 2
58
+ - total_train_batch_size: 8
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 10
62
+ - num_epochs: 100.0
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
69
+ | 4.6468 | 0.98 | 22 | 3.2315 | 1.0 |
70
+ | 1.5745 | 1.98 | 44 | 3.1603 | 1.0 |
71
+ | 1.465 | 2.98 | 66 | 2.2551 | 1.0 |
72
+ | 1.3168 | 3.98 | 88 | 1.8461 | 1.0 |
73
+ | 1.1359 | 4.98 | 110 | 1.4874 | 0.9797 |
74
+ | 0.9769 | 5.98 | 132 | 1.7359 | 0.5495 |
75
+ | 0.9019 | 6.98 | 154 | 1.5833 | 0.5268 |
76
+ | 0.8057 | 7.98 | 176 | 1.4892 | 0.5304 |
77
+ | 1.0845 | 8.98 | 198 | 1.3939 | 0.5197 |
78
+ | 0.7562 | 9.98 | 220 | 1.1238 | 0.5447 |
79
+ | 0.7259 | 10.98 | 242 | 1.2936 | 0.5006 |
80
+ | 0.7318 | 11.98 | 264 | 1.2763 | 0.4660 |
81
+ | 0.6452 | 12.98 | 286 | 1.2947 | 0.4779 |
82
+ | 0.6353 | 13.98 | 308 | 1.1925 | 0.4517 |
83
+ | 0.6463 | 14.98 | 330 | 0.8667 | 0.4100 |
84
+ | 0.5381 | 15.98 | 352 | 1.1243 | 0.3909 |
85
+ | 0.5637 | 16.98 | 374 | 0.8683 | 0.3754 |
86
+ | 0.6149 | 17.98 | 396 | 1.1040 | 0.3731 |
87
+ | 0.6138 | 18.98 | 418 | 1.1068 | 0.3850 |
88
+ | 0.7381 | 19.98 | 440 | 0.9203 | 0.3623 |
89
+ | 0.5064 | 20.98 | 462 | 0.8806 | 0.3540 |
90
+ | 0.4731 | 21.98 | 484 | 0.7259 | 0.3623 |
91
+ | 0.5232 | 22.98 | 506 | 0.7935 | 0.3516 |
92
+ | 0.4689 | 23.98 | 528 | 0.7771 | 0.3540 |
93
+ | 0.4902 | 24.98 | 550 | 0.6897 | 0.3909 |
94
+ | 0.4079 | 25.98 | 572 | 0.8030 | 0.3552 |
95
+ | 0.5045 | 26.98 | 594 | 0.6778 | 0.3790 |
96
+ | 0.4373 | 27.98 | 616 | 0.7456 | 0.3695 |
97
+ | 0.4366 | 28.98 | 638 | 0.7009 | 0.3433 |
98
+ | 0.3944 | 29.98 | 660 | 0.6841 | 0.3468 |
99
+ | 0.4206 | 30.98 | 682 | 0.7093 | 0.3373 |
100
+ | 0.3949 | 31.98 | 704 | 0.6901 | 0.3576 |
101
+ | 0.4416 | 32.98 | 726 | 0.6762 | 0.3397 |
102
+ | 0.4248 | 33.98 | 748 | 0.7196 | 0.3540 |
103
+ | 0.4214 | 34.98 | 770 | 0.6669 | 0.3254 |
104
+ | 0.416 | 35.98 | 792 | 0.6422 | 0.3445 |
105
+ | 0.3687 | 36.98 | 814 | 0.6345 | 0.3504 |
106
+ | 0.4119 | 37.98 | 836 | 0.6306 | 0.3385 |
107
+ | 0.359 | 38.98 | 858 | 0.6538 | 0.3576 |
108
+ | 0.359 | 39.98 | 880 | 0.6613 | 0.3349 |
109
+ | 0.3488 | 40.98 | 902 | 0.5976 | 0.3468 |
110
+ | 0.3543 | 41.98 | 924 | 0.6327 | 0.3433 |
111
+ | 0.3647 | 42.98 | 946 | 0.6208 | 0.3600 |
112
+ | 0.3529 | 43.98 | 968 | 0.6008 | 0.3492 |
113
+ | 0.3691 | 44.98 | 990 | 0.6065 | 0.3492 |
114
+ | 0.329 | 45.98 | 1012 | 0.6288 | 0.3373 |
115
+ | 0.3357 | 46.98 | 1034 | 0.5760 | 0.3480 |
116
+ | 0.3318 | 47.98 | 1056 | 0.5637 | 0.3564 |
117
+ | 0.3181 | 48.98 | 1078 | 0.5560 | 0.3468 |
118
+ | 0.3313 | 49.98 | 1100 | 0.5905 | 0.3337 |
119
+ | 0.3059 | 50.98 | 1122 | 0.5443 | 0.3278 |
120
+ | 0.3375 | 51.98 | 1144 | 0.5695 | 0.3576 |
121
+ | 0.3191 | 52.98 | 1166 | 0.5874 | 0.3385 |
122
+ | 0.3115 | 53.98 | 1188 | 0.5264 | 0.3635 |
123
+ | 0.3044 | 54.98 | 1210 | 0.5480 | 0.3433 |
124
+ | 0.3256 | 55.98 | 1232 | 0.5677 | 0.3385 |
125
+ | 0.2938 | 56.98 | 1254 | 0.5597 | 0.3445 |
126
+ | 0.2853 | 57.98 | 1276 | 0.5942 | 0.3373 |
127
+ | 0.3348 | 58.98 | 1298 | 0.5733 | 0.3421 |
128
+ | 0.3024 | 59.98 | 1320 | 0.5604 | 0.3433 |
129
+ | 0.2655 | 60.98 | 1342 | 0.5348 | 0.3468 |
130
+ | 0.3029 | 61.98 | 1364 | 0.5752 | 0.3206 |
131
+ | 0.3435 | 62.98 | 1386 | 0.5489 | 0.3063 |
132
+ | 0.3125 | 63.98 | 1408 | 0.5736 | 0.3075 |
133
+ | 0.263 | 64.98 | 1430 | 0.5505 | 0.3206 |
134
+ | 0.2665 | 65.98 | 1452 | 0.5391 | 0.3230 |
135
+ | 0.299 | 66.98 | 1474 | 0.5389 | 0.3135 |
136
+ | 0.2909 | 67.98 | 1496 | 0.5841 | 0.3099 |
137
+ | 0.2988 | 68.98 | 1518 | 0.5847 | 0.3004 |
138
+ | 0.2879 | 69.98 | 1540 | 0.5941 | 0.2968 |
139
+ | 0.2802 | 70.98 | 1562 | 0.6612 | 0.2920 |
140
+ | 0.2877 | 71.98 | 1584 | 0.5641 | 0.3051 |
141
+ | 0.2727 | 72.98 | 1606 | 0.6138 | 0.3063 |
142
+ | 0.2668 | 73.98 | 1628 | 0.6087 | 0.2920 |
143
+ | 0.2675 | 74.98 | 1650 | 0.5876 | 0.2932 |
144
+ | 0.264 | 75.98 | 1672 | 0.6043 | 0.2980 |
145
+ | 0.2352 | 76.98 | 1694 | 0.5829 | 0.2932 |
146
+ | 0.2494 | 77.98 | 1716 | 0.5775 | 0.3063 |
147
+ | 0.2621 | 78.98 | 1738 | 0.5676 | 0.2956 |
148
+ | 0.2788 | 79.98 | 1760 | 0.5864 | 0.2932 |
149
+ | 0.2615 | 80.98 | 1782 | 0.5754 | 0.3015 |
150
+ | 0.2542 | 81.98 | 1804 | 0.5651 | 0.3027 |
151
+ | 0.2641 | 82.98 | 1826 | 0.5731 | 0.3004 |
152
+ | 0.2532 | 83.98 | 1848 | 0.5782 | 0.2968 |
153
+ | 0.2645 | 84.98 | 1870 | 0.5718 | 0.3039 |
154
+ | 0.2296 | 85.98 | 1892 | 0.5628 | 0.3147 |
155
+ | 0.2394 | 86.98 | 1914 | 0.5920 | 0.3027 |
156
+ | 0.2636 | 87.98 | 1936 | 0.6085 | 0.2968 |
157
+ | 0.2371 | 88.98 | 1958 | 0.5809 | 0.3075 |
158
+ | 0.2364 | 89.98 | 1980 | 0.5927 | 0.3039 |
159
+ | 0.2812 | 90.98 | 2002 | 0.5713 | 0.3123 |
160
+ | 0.2141 | 91.98 | 2024 | 0.5743 | 0.3039 |
161
+ | 0.2919 | 92.98 | 2046 | 0.5837 | 0.3063 |
162
+ | 0.2288 | 93.98 | 2068 | 0.5860 | 0.3015 |
163
+ | 0.2585 | 94.98 | 2090 | 0.5776 | 0.3147 |
164
+ | 0.2529 | 95.98 | 2112 | 0.5625 | 0.3159 |
165
+ | 0.2343 | 96.98 | 2134 | 0.5700 | 0.3087 |
166
+ | 0.2567 | 97.98 | 2156 | 0.5729 | 0.3087 |
167
+ | 0.2448 | 98.98 | 2178 | 0.5728 | 0.3111 |
168
+ | 0.2501 | 99.98 | 2200 | 0.5744 | 0.3099 |
169
+
170
+
171
+ ### Framework versions
172
+
173
+ - Transformers 4.25.0.dev0
174
+ - Pytorch 1.8.1+cu111
175
+ - Datasets 2.7.1.dev0
176
+ - Tokenizers 0.13.2