Hugging Face's logo

gary109
/
ai-light-dance_drums_ft_pretrain_wav2vec2-base-new-v6-1

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
d4576b6
•
1 Parent(s): c1cde70

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-v6-1
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-mdb-enst2
18
+ split: train
19
+ args: onset-idmt-mdb-enst2
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 0.3770560944749051
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-v6-1
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: 0.6990
34
+ - Wer: 0.3771
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: 4
58
+ - total_train_batch_size: 16
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 30
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
+ | 17.2739 | 0.99 | 35 | 2.9041 | 1.0 |
70
+ | 1.8424 | 1.99 | 70 | 3.5055 | 1.0 |
71
+ | 1.7092 | 2.99 | 105 | 2.0046 | 1.0 |
72
+ | 1.5022 | 3.99 | 140 | 1.9662 | 0.9675 |
73
+ | 1.2964 | 4.99 | 175 | 1.9017 | 0.5504 |
74
+ | 1.1235 | 5.99 | 210 | 1.9875 | 0.4644 |
75
+ | 1.1056 | 6.99 | 245 | 1.8791 | 0.4762 |
76
+ | 0.8907 | 7.99 | 280 | 1.4811 | 0.4673 |
77
+ | 0.8605 | 8.99 | 315 | 1.9114 | 0.4479 |
78
+ | 0.8498 | 9.99 | 350 | 1.2107 | 0.4728 |
79
+ | 0.7205 | 10.99 | 385 | 1.5744 | 0.4526 |
80
+ | 0.8417 | 11.99 | 420 | 1.4689 | 0.4534 |
81
+ | 0.7734 | 12.99 | 455 | 1.3531 | 0.4551 |
82
+ | 0.7762 | 13.99 | 490 | 1.2924 | 0.4665 |
83
+ | 0.6812 | 14.99 | 525 | 1.0827 | 0.4100 |
84
+ | 0.7245 | 15.99 | 560 | 1.4070 | 0.4353 |
85
+ | 0.6508 | 16.99 | 595 | 1.0520 | 0.4087 |
86
+ | 0.7144 | 17.99 | 630 | 1.0729 | 0.4209 |
87
+ | 0.6566 | 18.99 | 665 | 1.1672 | 0.4053 |
88
+ | 0.5802 | 19.99 | 700 | 1.0129 | 0.4015 |
89
+ | 0.5924 | 20.99 | 735 | 1.0762 | 0.4007 |
90
+ | 0.7051 | 21.99 | 770 | 1.0253 | 0.4028 |
91
+ | 0.5669 | 22.99 | 805 | 1.0526 | 0.4188 |
92
+ | 0.6209 | 23.99 | 840 | 1.0177 | 0.4213 |
93
+ | 0.635 | 24.99 | 875 | 0.9299 | 0.4019 |
94
+ | 0.5914 | 25.99 | 910 | 1.0058 | 0.4142 |
95
+ | 0.5983 | 26.99 | 945 | 0.9720 | 0.4142 |
96
+ | 0.5631 | 27.99 | 980 | 0.8983 | 0.4028 |
97
+ | 0.552 | 28.99 | 1015 | 0.9148 | 0.4184 |
98
+ | 0.5213 | 29.99 | 1050 | 1.0817 | 0.4142 |
99
+ | 0.5387 | 30.99 | 1085 | 0.9432 | 0.4188 |
100
+ | 0.5276 | 31.99 | 1120 | 1.1207 | 0.4007 |
101
+ | 0.5778 | 32.99 | 1155 | 0.9254 | 0.4150 |
102
+ | 0.5001 | 33.99 | 1190 | 1.0393 | 0.4192 |
103
+ | 0.5329 | 34.99 | 1225 | 0.9109 | 0.3965 |
104
+ | 0.5168 | 35.99 | 1260 | 0.8983 | 0.4298 |
105
+ | 0.4918 | 36.99 | 1295 | 0.8412 | 0.4087 |
106
+ | 0.5651 | 37.99 | 1330 | 0.8560 | 0.4218 |
107
+ | 0.438 | 38.99 | 1365 | 0.8556 | 0.4171 |
108
+ | 0.4808 | 39.99 | 1400 | 0.8320 | 0.4175 |
109
+ | 0.5372 | 40.99 | 1435 | 0.9745 | 0.3956 |
110
+ | 0.4814 | 41.99 | 1470 | 0.8033 | 0.4121 |
111
+ | 0.4416 | 42.99 | 1505 | 0.8195 | 0.3990 |
112
+ | 0.4958 | 43.99 | 1540 | 0.8264 | 0.3956 |
113
+ | 0.4665 | 44.99 | 1575 | 0.8172 | 0.4070 |
114
+ | 0.4196 | 45.99 | 1610 | 0.7971 | 0.3952 |
115
+ | 0.4088 | 46.99 | 1645 | 0.7417 | 0.3880 |
116
+ | 0.4308 | 47.99 | 1680 | 0.7806 | 0.3931 |
117
+ | 0.4173 | 48.99 | 1715 | 0.7380 | 0.3922 |
118
+ | 0.4653 | 49.99 | 1750 | 0.8962 | 0.4028 |
119
+ | 0.4406 | 50.99 | 1785 | 0.7790 | 0.3935 |
120
+ | 0.4664 | 51.99 | 1820 | 0.9173 | 0.3893 |
121
+ | 0.4486 | 52.99 | 1855 | 0.8235 | 0.3922 |
122
+ | 0.4137 | 53.99 | 1890 | 0.8032 | 0.3927 |
123
+ | 0.4402 | 54.99 | 1925 | 0.7658 | 0.3830 |
124
+ | 0.4101 | 55.99 | 1960 | 0.8621 | 0.3994 |
125
+ | 0.5239 | 56.99 | 1995 | 0.7903 | 0.3956 |
126
+ | 0.4151 | 57.99 | 2030 | 0.7849 | 0.3872 |
127
+ | 0.4766 | 58.99 | 2065 | 0.8306 | 0.3918 |
128
+ | 0.4882 | 59.99 | 2100 | 0.8134 | 0.3927 |
129
+ | 0.4583 | 60.99 | 2135 | 0.9527 | 0.3851 |
130
+ | 0.4284 | 61.99 | 2170 | 0.9743 | 0.3998 |
131
+ | 0.46 | 62.99 | 2205 | 0.7807 | 0.3830 |
132
+ | 0.4039 | 63.99 | 2240 | 0.8864 | 0.3884 |
133
+ | 0.3868 | 64.99 | 2275 | 0.7304 | 0.3817 |
134
+ | 0.3934 | 65.99 | 2310 | 0.8758 | 0.3846 |
135
+ | 0.3776 | 66.99 | 2345 | 0.8156 | 0.3762 |
136
+ | 0.3499 | 67.99 | 2380 | 0.8143 | 0.3889 |
137
+ | 0.4055 | 68.99 | 2415 | 0.7503 | 0.3796 |
138
+ | 0.3505 | 69.99 | 2450 | 0.7138 | 0.3804 |
139
+ | 0.3755 | 70.99 | 2485 | 0.8072 | 0.3800 |
140
+ | 0.3594 | 71.99 | 2520 | 0.7692 | 0.3851 |
141
+ | 0.3167 | 72.99 | 2555 | 0.6995 | 0.3745 |
142
+ | 0.3915 | 73.99 | 2590 | 0.6712 | 0.3762 |
143
+ | 0.3741 | 74.99 | 2625 | 0.7139 | 0.3800 |
144
+ | 0.3708 | 75.99 | 2660 | 0.7065 | 0.3834 |
145
+ | 0.3731 | 76.99 | 2695 | 0.7316 | 0.3754 |
146
+ | 0.3785 | 77.99 | 2730 | 0.7071 | 0.3758 |
147
+ | 0.3466 | 78.99 | 2765 | 0.7362 | 0.3834 |
148
+ | 0.3505 | 79.99 | 2800 | 0.6965 | 0.3800 |
149
+ | 0.4003 | 80.99 | 2835 | 0.7521 | 0.3766 |
150
+ | 0.3723 | 81.99 | 2870 | 0.7617 | 0.3749 |
151
+ | 0.4029 | 82.99 | 2905 | 0.7659 | 0.3813 |
152
+ | 0.3478 | 83.99 | 2940 | 0.7077 | 0.3834 |
153
+ | 0.3363 | 84.99 | 2975 | 0.7333 | 0.3787 |
154
+ | 0.4228 | 85.99 | 3010 | 0.7196 | 0.3745 |
155
+ | 0.3823 | 86.99 | 3045 | 0.7195 | 0.3754 |
156
+ | 0.3574 | 87.99 | 3080 | 0.7137 | 0.3796 |
157
+ | 0.3371 | 88.99 | 3115 | 0.7164 | 0.3762 |
158
+ | 0.3548 | 89.99 | 3150 | 0.7766 | 0.3792 |
159
+ | 0.4042 | 90.99 | 3185 | 0.7588 | 0.3766 |
160
+ | 0.3989 | 91.99 | 3220 | 0.7311 | 0.3775 |
161
+ | 0.3625 | 92.99 | 3255 | 0.7475 | 0.3745 |
162
+ | 0.3036 | 93.99 | 3290 | 0.7138 | 0.3716 |
163
+ | 0.5157 | 94.99 | 3325 | 0.7246 | 0.3787 |
164
+ | 0.4072 | 95.99 | 3360 | 0.7322 | 0.3762 |
165
+ | 0.3406 | 96.99 | 3395 | 0.7134 | 0.3771 |
166
+ | 0.2987 | 97.99 | 3430 | 0.6951 | 0.3754 |
167
+ | 0.3355 | 98.99 | 3465 | 0.7005 | 0.3766 |
168
+ | 0.341 | 99.99 | 3500 | 0.6990 | 0.3771 |
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