Hugging Face's logo

gary109
/
ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-enst-2

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
gary109/AI_Light_Dance
Generated from Trainer
Model card Files Metrics Community
1
gary109 commited on
Commit
07bbb0f
·
1 Parent(s): 939be1f

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_onset-idmt-mdb-enst-2
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-enst-2
18
+ split: train
19
+ args: onset-idmt-mdb-enst-2
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 0.34289329396878954
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_onset-idmt-mdb-enst-2
30
+
31
+ This model is a fine-tuned version of [gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-2](https://huggingface.co/gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-mdb-2) on the ai_light_dance dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.7762
34
+ - Wer: 0.3429
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: 0.0003
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
+ | 1.4226 | 0.99 | 35 | 2.0435 | 0.4154 |
70
+ | 0.8744 | 1.99 | 70 | 1.7193 | 0.4382 |
71
+ | 0.9474 | 2.99 | 105 | 1.7853 | 0.4374 |
72
+ | 0.8316 | 3.99 | 140 | 1.2827 | 0.4306 |
73
+ | 0.8336 | 4.99 | 175 | 1.0676 | 0.4040 |
74
+ | 0.7345 | 5.99 | 210 | 1.5364 | 0.4264 |
75
+ | 0.6666 | 6.99 | 245 | 1.4284 | 0.4585 |
76
+ | 0.6677 | 7.99 | 280 | 0.9475 | 0.4003 |
77
+ | 0.6779 | 8.99 | 315 | 1.1172 | 0.4209 |
78
+ | 0.6503 | 9.99 | 350 | 0.8999 | 0.3834 |
79
+ | 0.6159 | 10.99 | 385 | 1.1501 | 0.4386 |
80
+ | 0.6831 | 11.99 | 420 | 1.0860 | 0.3825 |
81
+ | 0.5959 | 12.99 | 455 | 0.9410 | 0.4045 |
82
+ | 0.7154 | 13.99 | 490 | 1.0463 | 0.3821 |
83
+ | 0.6094 | 14.99 | 525 | 0.8598 | 0.3965 |
84
+ | 0.6929 | 15.99 | 560 | 0.9494 | 0.3931 |
85
+ | 0.7627 | 16.99 | 595 | 0.8060 | 0.3948 |
86
+ | 0.601 | 17.99 | 630 | 0.9890 | 0.3965 |
87
+ | 0.546 | 18.99 | 665 | 0.8059 | 0.3990 |
88
+ | 0.5222 | 19.99 | 700 | 0.6379 | 0.3792 |
89
+ | 0.5802 | 20.99 | 735 | 0.6995 | 0.3661 |
90
+ | 0.5731 | 21.99 | 770 | 0.8405 | 0.3606 |
91
+ | 0.5462 | 22.99 | 805 | 0.6667 | 0.3965 |
92
+ | 0.6057 | 23.99 | 840 | 0.8396 | 0.3762 |
93
+ | 0.5323 | 24.99 | 875 | 0.9054 | 0.3952 |
94
+ | 0.683 | 25.99 | 910 | 0.6898 | 0.4062 |
95
+ | 0.525 | 26.99 | 945 | 0.7245 | 0.3884 |
96
+ | 0.4885 | 27.99 | 980 | 0.8076 | 0.4049 |
97
+ | 0.4653 | 28.99 | 1015 | 0.8100 | 0.3838 |
98
+ | 0.4827 | 29.99 | 1050 | 0.7247 | 0.3863 |
99
+ | 0.4839 | 30.99 | 1085 | 0.7009 | 0.3817 |
100
+ | 0.4982 | 31.99 | 1120 | 0.7637 | 0.3914 |
101
+ | 0.6105 | 32.99 | 1155 | 0.7343 | 0.3914 |
102
+ | 0.4936 | 33.99 | 1190 | 0.7390 | 0.3762 |
103
+ | 0.4674 | 34.99 | 1225 | 0.6724 | 0.3581 |
104
+ | 0.4677 | 35.99 | 1260 | 0.6730 | 0.3488 |
105
+ | 0.516 | 36.99 | 1295 | 0.6956 | 0.3728 |
106
+ | 0.4507 | 37.99 | 1330 | 0.6483 | 0.3615 |
107
+ | 0.4207 | 38.99 | 1365 | 0.7718 | 0.3484 |
108
+ | 0.4803 | 39.99 | 1400 | 0.8316 | 0.3775 |
109
+ | 0.3946 | 40.99 | 1435 | 0.8322 | 0.3568 |
110
+ | 0.411 | 41.99 | 1470 | 0.9933 | 0.3707 |
111
+ | 0.4405 | 42.99 | 1505 | 0.8789 | 0.3943 |
112
+ | 0.5124 | 43.99 | 1540 | 0.9030 | 0.3707 |
113
+ | 0.5959 | 44.99 | 1575 | 0.7809 | 0.3948 |
114
+ | 0.3841 | 45.99 | 1610 | 0.7716 | 0.3965 |
115
+ | 0.3975 | 46.99 | 1645 | 0.7064 | 0.3931 |
116
+ | 1.4983 | 47.99 | 1680 | 3.2866 | 0.3627 |
117
+ | 0.3962 | 48.99 | 1715 | 0.6486 | 0.3648 |
118
+ | 0.4422 | 49.99 | 1750 | 0.8450 | 0.3779 |
119
+ | 0.4198 | 50.99 | 1785 | 0.7628 | 0.3564 |
120
+ | 0.3577 | 51.99 | 1820 | 0.7553 | 0.3678 |
121
+ | 0.4425 | 52.99 | 1855 | 0.7566 | 0.3716 |
122
+ | 0.3492 | 53.99 | 1890 | 0.7710 | 0.3631 |
123
+ | 0.3731 | 54.99 | 1925 | 0.7737 | 0.3627 |
124
+ | 0.3868 | 55.99 | 1960 | 0.7021 | 0.3572 |
125
+ | 0.3311 | 56.99 | 1995 | 0.6603 | 0.3518 |
126
+ | 0.3993 | 57.99 | 2030 | 0.6664 | 0.3581 |
127
+ | 0.4226 | 58.99 | 2065 | 0.6813 | 0.3551 |
128
+ | 0.4143 | 59.99 | 2100 | 0.6567 | 0.3568 |
129
+ | 0.3623 | 60.99 | 2135 | 0.6568 | 0.3454 |
130
+ | 0.3228 | 61.99 | 2170 | 0.7326 | 0.3568 |
131
+ | 0.3204 | 62.99 | 2205 | 0.7277 | 0.3640 |
132
+ | 0.377 | 63.99 | 2240 | 0.7145 | 0.3585 |
133
+ | 0.3487 | 64.99 | 2275 | 0.6943 | 0.3505 |
134
+ | 0.343 | 65.99 | 2310 | 0.7461 | 0.3395 |
135
+ | 0.3251 | 66.99 | 2345 | 0.7442 | 0.3564 |
136
+ | 0.3135 | 67.99 | 2380 | 0.7331 | 0.3530 |
137
+ | 0.381 | 68.99 | 2415 | 0.7306 | 0.3513 |
138
+ | 0.3319 | 69.99 | 2450 | 0.8495 | 0.3484 |
139
+ | 0.3552 | 70.99 | 2485 | 0.7546 | 0.3551 |
140
+ | 0.3292 | 71.99 | 2520 | 0.7483 | 0.3450 |
141
+ | 0.3041 | 72.99 | 2555 | 0.7305 | 0.3522 |
142
+ | 0.3606 | 73.99 | 2590 | 0.7358 | 0.3484 |
143
+ | 0.3629 | 74.99 | 2625 | 0.7709 | 0.3446 |
144
+ | 0.3409 | 75.99 | 2660 | 0.7568 | 0.3585 |
145
+ | 0.3315 | 76.99 | 2695 | 0.7466 | 0.3475 |
146
+ | 0.2934 | 77.99 | 2730 | 0.7351 | 0.3496 |
147
+ | 0.3366 | 78.99 | 2765 | 0.8014 | 0.3484 |
148
+ | 0.3176 | 79.99 | 2800 | 0.8014 | 0.3420 |
149
+ | 0.3319 | 80.99 | 2835 | 0.7996 | 0.3437 |
150
+ | 0.2967 | 81.99 | 2870 | 0.8156 | 0.3412 |
151
+ | 0.3137 | 82.99 | 2905 | 0.8025 | 0.3361 |
152
+ | 0.3133 | 83.99 | 2940 | 0.7784 | 0.3416 |
153
+ | 0.3134 | 84.99 | 2975 | 0.7894 | 0.3336 |
154
+ | 0.3216 | 85.99 | 3010 | 0.8331 | 0.3395 |
155
+ | 0.365 | 86.99 | 3045 | 0.7980 | 0.3353 |
156
+ | 0.2962 | 87.99 | 3080 | 0.7965 | 0.3404 |
157
+ | 0.3126 | 88.99 | 3115 | 0.7470 | 0.3420 |
158
+ | 0.2843 | 89.99 | 3150 | 0.7788 | 0.3404 |
159
+ | 0.2967 | 90.99 | 3185 | 0.7902 | 0.3374 |
160
+ | 0.3171 | 91.99 | 3220 | 0.8022 | 0.3404 |
161
+ | 0.3069 | 92.99 | 3255 | 0.7999 | 0.3345 |
162
+ | 0.3571 | 93.99 | 3290 | 0.7896 | 0.3404 |
163
+ | 0.2805 | 94.99 | 3325 | 0.7831 | 0.3391 |
164
+ | 0.3099 | 95.99 | 3360 | 0.7909 | 0.3366 |
165
+ | 0.2868 | 96.99 | 3395 | 0.7918 | 0.3395 |
166
+ | 0.2626 | 97.99 | 3430 | 0.7766 | 0.3429 |
167
+ | 0.2634 | 98.99 | 3465 | 0.7770 | 0.3437 |
168
+ | 0.288 | 99.99 | 3500 | 0.7762 | 0.3429 |
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