Hugging Face's logo

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

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
gary109/AI_Light_Dance
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
gary109 commited on
Commit
650d379
·
1 Parent(s): 2ea6fca

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-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-2
18
+ split: train
19
+ args: onset-idmt-mdb-2
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 0.19469026548672566
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-2
30
+
31
+ This model is a fine-tuned version of [gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-2](https://huggingface.co/gary109/ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-idmt-2) on the ai_light_dance dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 0.4625
34
+ - Wer: 0.1947
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
+ | 22.7802 | 0.98 | 11 | 60.1549 | 0.9882 |
70
+ | 13.7635 | 1.98 | 22 | 18.1822 | 0.9985 |
71
+ | 3.4364 | 2.98 | 33 | 1.2339 | 0.7316 |
72
+ | 1.0479 | 3.98 | 44 | 0.8433 | 0.4086 |
73
+ | 0.739 | 4.98 | 55 | 0.7657 | 0.3097 |
74
+ | 0.6492 | 5.98 | 66 | 0.8034 | 0.2994 |
75
+ | 0.6044 | 6.98 | 77 | 0.6401 | 0.3333 |
76
+ | 0.5662 | 7.98 | 88 | 0.7298 | 0.2611 |
77
+ | 0.5321 | 8.98 | 99 | 0.8126 | 0.2979 |
78
+ | 0.5037 | 9.98 | 110 | 0.7135 | 0.2994 |
79
+ | 0.4823 | 10.98 | 121 | 0.5976 | 0.2655 |
80
+ | 0.4622 | 11.98 | 132 | 0.6875 | 0.2448 |
81
+ | 0.4761 | 12.98 | 143 | 0.6402 | 0.2463 |
82
+ | 0.4296 | 13.98 | 154 | 0.8217 | 0.2448 |
83
+ | 0.4655 | 14.98 | 165 | 0.7825 | 0.2552 |
84
+ | 0.4122 | 15.98 | 176 | 0.7121 | 0.2448 |
85
+ | 0.4234 | 16.98 | 187 | 0.8301 | 0.2670 |
86
+ | 0.441 | 17.98 | 198 | 0.7343 | 0.2640 |
87
+ | 0.4781 | 18.98 | 209 | 0.7388 | 0.2139 |
88
+ | 0.4006 | 19.98 | 220 | 0.6700 | 0.2522 |
89
+ | 0.42 | 20.98 | 231 | 0.5540 | 0.2493 |
90
+ | 0.4289 | 21.98 | 242 | 0.9950 | 0.2493 |
91
+ | 0.4014 | 22.98 | 253 | 0.7283 | 0.2522 |
92
+ | 0.3397 | 23.98 | 264 | 0.8327 | 0.2655 |
93
+ | 0.3879 | 24.98 | 275 | 0.9388 | 0.2906 |
94
+ | 0.3445 | 25.98 | 286 | 0.7623 | 0.2522 |
95
+ | 0.3933 | 26.98 | 297 | 0.9125 | 0.2419 |
96
+ | 0.3173 | 27.98 | 308 | 0.7447 | 0.2448 |
97
+ | 0.3734 | 28.98 | 319 | 0.6601 | 0.2935 |
98
+ | 0.3347 | 29.98 | 330 | 0.7022 | 0.2699 |
99
+ | 0.3564 | 30.98 | 341 | 0.7488 | 0.2920 |
100
+ | 0.3371 | 31.98 | 352 | 0.6413 | 0.2581 |
101
+ | 0.355 | 32.98 | 363 | 0.5131 | 0.2375 |
102
+ | 0.3648 | 33.98 | 374 | 0.5808 | 0.2286 |
103
+ | 0.3209 | 34.98 | 385 | 0.5392 | 0.2257 |
104
+ | 0.3522 | 35.98 | 396 | 0.4411 | 0.2227 |
105
+ | 0.3252 | 36.98 | 407 | 0.4693 | 0.2109 |
106
+ | 0.3216 | 37.98 | 418 | 0.4621 | 0.2065 |
107
+ | 0.3119 | 38.98 | 429 | 0.5094 | 0.2168 |
108
+ | 0.3247 | 39.98 | 440 | 0.4897 | 0.2316 |
109
+ | 0.3246 | 40.98 | 451 | 0.6471 | 0.2212 |
110
+ | 0.2997 | 41.98 | 462 | 0.5569 | 0.2153 |
111
+ | 0.2969 | 42.98 | 473 | 0.4766 | 0.2094 |
112
+ | 0.3202 | 43.98 | 484 | 0.4978 | 0.2316 |
113
+ | 0.3093 | 44.98 | 495 | 0.4776 | 0.2183 |
114
+ | 0.298 | 45.98 | 506 | 0.5008 | 0.2198 |
115
+ | 0.3151 | 46.98 | 517 | 0.4811 | 0.2080 |
116
+ | 0.2824 | 47.98 | 528 | 0.5011 | 0.2065 |
117
+ | 0.3089 | 48.98 | 539 | 0.5131 | 0.2139 |
118
+ | 0.3064 | 49.98 | 550 | 0.4749 | 0.2227 |
119
+ | 0.2734 | 50.98 | 561 | 0.5397 | 0.2080 |
120
+ | 0.2911 | 51.98 | 572 | 0.4975 | 0.2035 |
121
+ | 0.2889 | 52.98 | 583 | 0.4633 | 0.2168 |
122
+ | 0.2523 | 53.98 | 594 | 0.4589 | 0.2242 |
123
+ | 0.272 | 54.98 | 605 | 0.4856 | 0.2124 |
124
+ | 0.2733 | 55.98 | 616 | 0.4474 | 0.2242 |
125
+ | 0.2856 | 56.98 | 627 | 0.4534 | 0.2271 |
126
+ | 0.2402 | 57.98 | 638 | 0.4346 | 0.2242 |
127
+ | 0.2567 | 58.98 | 649 | 0.5014 | 0.2286 |
128
+ | 0.28 | 59.98 | 660 | 0.4428 | 0.2183 |
129
+ | 0.2541 | 60.98 | 671 | 0.4876 | 0.2227 |
130
+ | 0.2544 | 61.98 | 682 | 0.4705 | 0.2050 |
131
+ | 0.2786 | 62.98 | 693 | 0.4449 | 0.2021 |
132
+ | 0.2524 | 63.98 | 704 | 0.5585 | 0.2094 |
133
+ | 0.2524 | 64.98 | 715 | 0.5179 | 0.2109 |
134
+ | 0.2852 | 65.98 | 726 | 0.5063 | 0.2198 |
135
+ | 0.2393 | 66.98 | 737 | 0.4768 | 0.1991 |
136
+ | 0.2522 | 67.98 | 748 | 0.4473 | 0.1932 |
137
+ | 0.2768 | 68.98 | 759 | 0.4714 | 0.1991 |
138
+ | 0.2463 | 69.98 | 770 | 0.4948 | 0.1947 |
139
+ | 0.2379 | 70.98 | 781 | 0.4978 | 0.1932 |
140
+ | 0.2343 | 71.98 | 792 | 0.4526 | 0.1903 |
141
+ | 0.3377 | 72.98 | 803 | 0.4518 | 0.1962 |
142
+ | 0.2683 | 73.98 | 814 | 0.4457 | 0.2109 |
143
+ | 0.2371 | 74.98 | 825 | 0.4564 | 0.2021 |
144
+ | 0.2438 | 75.98 | 836 | 0.4876 | 0.2094 |
145
+ | 0.2408 | 76.98 | 847 | 0.4386 | 0.2021 |
146
+ | 0.2323 | 77.98 | 858 | 0.4513 | 0.1991 |
147
+ | 0.271 | 78.98 | 869 | 0.4874 | 0.2021 |
148
+ | 0.229 | 79.98 | 880 | 0.4882 | 0.2065 |
149
+ | 0.224 | 80.98 | 891 | 0.4981 | 0.1991 |
150
+ | 0.2442 | 81.98 | 902 | 0.5448 | 0.2021 |
151
+ | 0.2075 | 82.98 | 913 | 0.4626 | 0.1991 |
152
+ | 0.2314 | 83.98 | 924 | 0.4706 | 0.2065 |
153
+ | 0.2208 | 84.98 | 935 | 0.5073 | 0.2035 |
154
+ | 0.2547 | 85.98 | 946 | 0.4818 | 0.1962 |
155
+ | 0.2895 | 86.98 | 957 | 0.4931 | 0.1991 |
156
+ | 0.1988 | 87.98 | 968 | 0.4702 | 0.2006 |
157
+ | 0.2383 | 88.98 | 979 | 0.4682 | 0.1991 |
158
+ | 0.2332 | 89.98 | 990 | 0.4575 | 0.2065 |
159
+ | 0.1983 | 90.98 | 1001 | 0.4706 | 0.1991 |
160
+ | 0.2182 | 91.98 | 1012 | 0.4756 | 0.1991 |
161
+ | 0.2161 | 92.98 | 1023 | 0.4686 | 0.1962 |
162
+ | 0.2215 | 93.98 | 1034 | 0.4689 | 0.1932 |
163
+ | 0.2223 | 94.98 | 1045 | 0.4514 | 0.1888 |
164
+ | 0.2068 | 95.98 | 1056 | 0.4482 | 0.1888 |
165
+ | 0.2046 | 96.98 | 1067 | 0.4481 | 0.1858 |
166
+ | 0.2411 | 97.98 | 1078 | 0.4532 | 0.1903 |
167
+ | 0.2296 | 98.98 | 1089 | 0.4601 | 0.1932 |
168
+ | 0.2211 | 99.98 | 1100 | 0.4625 | 0.1947 |
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