Hugging Face's logo

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

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
814237f
•
1 Parent(s): b3c15d6

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
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
18
+ split: train
19
+ args: onset-idmt-mdb-enst
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 0.37368199072121466
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
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: 0.7173
34
+ - Wer: 0.3737
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
+ | 17.274 | 0.99 | 35 | 2.9045 | 1.0 |
70
+ | 1.8443 | 1.99 | 70 | 3.5065 | 1.0 |
71
+ | 1.709 | 2.99 | 105 | 2.0072 | 1.0 |
72
+ | 1.4981 | 3.99 | 140 | 1.9510 | 0.9688 |
73
+ | 1.2977 | 4.99 | 175 | 1.8863 | 0.5534 |
74
+ | 1.1257 | 5.99 | 210 | 1.9137 | 0.4833 |
75
+ | 1.1218 | 6.99 | 245 | 1.9707 | 0.4960 |
76
+ | 0.8878 | 7.99 | 280 | 1.4179 | 0.4774 |
77
+ | 0.8562 | 8.99 | 315 | 1.5276 | 0.4635 |
78
+ | 1.5769 | 9.99 | 350 | 1.1270 | 0.4509 |
79
+ | 0.796 | 10.99 | 385 | 1.2706 | 0.4496 |
80
+ | 0.8776 | 11.99 | 420 | 1.2372 | 0.4471 |
81
+ | 0.7417 | 12.99 | 455 | 1.2826 | 0.4382 |
82
+ | 0.8273 | 13.99 | 490 | 1.2425 | 0.4542 |
83
+ | 0.7164 | 14.99 | 525 | 1.1415 | 0.4192 |
84
+ | 0.7061 | 15.99 | 560 | 1.2315 | 0.4407 |
85
+ | 0.6553 | 16.99 | 595 | 0.9983 | 0.4112 |
86
+ | 0.7114 | 17.99 | 630 | 1.1510 | 0.4382 |
87
+ | 0.6467 | 18.99 | 665 | 1.0612 | 0.4049 |
88
+ | 0.6035 | 19.99 | 700 | 1.0360 | 0.4188 |
89
+ | 0.6058 | 20.99 | 735 | 1.0008 | 0.4137 |
90
+ | 0.682 | 21.99 | 770 | 1.1948 | 0.4209 |
91
+ | 0.566 | 22.99 | 805 | 1.0555 | 0.4133 |
92
+ | 0.5952 | 23.99 | 840 | 0.8615 | 0.4095 |
93
+ | 0.5889 | 24.99 | 875 | 1.0740 | 0.4302 |
94
+ | 0.5954 | 25.99 | 910 | 1.1465 | 0.4167 |
95
+ | 0.5615 | 26.99 | 945 | 0.8980 | 0.4074 |
96
+ | 0.5385 | 27.99 | 980 | 0.8443 | 0.4062 |
97
+ | 0.5097 | 28.99 | 1015 | 1.1464 | 0.4049 |
98
+ | 0.5224 | 29.99 | 1050 | 1.0213 | 0.4003 |
99
+ | 0.5226 | 30.99 | 1085 | 0.8601 | 0.4091 |
100
+ | 0.5303 | 31.99 | 1120 | 1.0191 | 0.3986 |
101
+ | 0.6457 | 32.99 | 1155 | 1.2443 | 0.4306 |
102
+ | 0.5305 | 33.99 | 1190 | 0.9872 | 0.4171 |
103
+ | 0.5179 | 34.99 | 1225 | 1.0433 | 0.3935 |
104
+ | 0.471 | 35.99 | 1260 | 1.0011 | 0.4074 |
105
+ | 0.473 | 36.99 | 1295 | 0.8887 | 0.3901 |
106
+ | 0.5465 | 37.99 | 1330 | 0.8612 | 0.3897 |
107
+ | 0.4584 | 38.99 | 1365 | 0.9581 | 0.4070 |
108
+ | 0.565 | 39.99 | 1400 | 1.0735 | 0.4083 |
109
+ | 0.4916 | 40.99 | 1435 | 0.8890 | 0.3906 |
110
+ | 0.4643 | 41.99 | 1470 | 0.7317 | 0.4040 |
111
+ | 0.4633 | 42.99 | 1505 | 0.9384 | 0.4142 |
112
+ | 0.4867 | 43.99 | 1540 | 0.8899 | 0.4074 |
113
+ | 0.4892 | 44.99 | 1575 | 0.8419 | 0.4053 |
114
+ | 0.4338 | 45.99 | 1610 | 0.8297 | 0.4024 |
115
+ | 0.4038 | 46.99 | 1645 | 0.9689 | 0.3825 |
116
+ | 0.4519 | 47.99 | 1680 | 0.8536 | 0.4053 |
117
+ | 0.4298 | 48.99 | 1715 | 0.9737 | 0.3796 |
118
+ | 0.4622 | 49.99 | 1750 | 0.9054 | 0.4074 |
119
+ | 0.4358 | 50.99 | 1785 | 0.7809 | 0.3813 |
120
+ | 0.4277 | 51.99 | 1820 | 0.8464 | 0.3922 |
121
+ | 0.4186 | 52.99 | 1855 | 0.8106 | 0.3956 |
122
+ | 0.413 | 53.99 | 1890 | 0.9219 | 0.3813 |
123
+ | 0.4262 | 54.99 | 1925 | 0.9600 | 0.3990 |
124
+ | 0.4542 | 55.99 | 1960 | 0.8444 | 0.4057 |
125
+ | 0.3966 | 56.99 | 1995 | 0.7814 | 0.3914 |
126
+ | 0.444 | 57.99 | 2030 | 0.8331 | 0.3771 |
127
+ | 0.4673 | 58.99 | 2065 | 0.7872 | 0.3960 |
128
+ | 0.483 | 59.99 | 2100 | 1.0760 | 0.4036 |
129
+ | 0.5059 | 60.99 | 2135 | 0.8133 | 0.3981 |
130
+ | 0.3927 | 61.99 | 2170 | 0.8601 | 0.4032 |
131
+ | 0.4297 | 62.99 | 2205 | 0.7363 | 0.3880 |
132
+ | 0.4034 | 63.99 | 2240 | 0.7639 | 0.4028 |
133
+ | 0.3731 | 64.99 | 2275 | 0.8137 | 0.3686 |
134
+ | 0.3793 | 65.99 | 2310 | 0.7646 | 0.3787 |
135
+ | 0.3593 | 66.99 | 2345 | 0.7878 | 0.3952 |
136
+ | 0.3616 | 67.99 | 2380 | 0.7936 | 0.4045 |
137
+ | 0.3991 | 68.99 | 2415 | 0.7425 | 0.3775 |
138
+ | 0.3709 | 69.99 | 2450 | 0.6933 | 0.3834 |
139
+ | 0.3886 | 70.99 | 2485 | 0.7044 | 0.3728 |
140
+ | 0.3624 | 71.99 | 2520 | 0.6916 | 0.3922 |
141
+ | 0.3477 | 72.99 | 2555 | 0.7245 | 0.3872 |
142
+ | 0.4116 | 73.99 | 2590 | 0.6823 | 0.3851 |
143
+ | 0.3956 | 74.99 | 2625 | 0.7743 | 0.3846 |
144
+ | 0.386 | 75.99 | 2660 | 0.7772 | 0.3943 |
145
+ | 0.3755 | 76.99 | 2695 | 0.7823 | 0.3741 |
146
+ | 0.3569 | 77.99 | 2730 | 0.7801 | 0.3880 |
147
+ | 0.3403 | 78.99 | 2765 | 0.7619 | 0.3783 |
148
+ | 0.3623 | 79.99 | 2800 | 0.7294 | 0.3834 |
149
+ | 0.4157 | 80.99 | 2835 | 0.7345 | 0.3855 |
150
+ | 0.3569 | 81.99 | 2870 | 0.7349 | 0.3804 |
151
+ | 0.3988 | 82.99 | 2905 | 0.7232 | 0.3834 |
152
+ | 0.3425 | 83.99 | 2940 | 0.7239 | 0.3792 |
153
+ | 0.353 | 84.99 | 2975 | 0.7367 | 0.3758 |
154
+ | 0.3756 | 85.99 | 3010 | 0.7283 | 0.3728 |
155
+ | 0.3702 | 86.99 | 3045 | 0.7044 | 0.3792 |
156
+ | 0.3339 | 87.99 | 3080 | 0.7279 | 0.3766 |
157
+ | 0.3161 | 88.99 | 3115 | 0.7680 | 0.3796 |
158
+ | 0.3573 | 89.99 | 3150 | 0.7498 | 0.3733 |
159
+ | 0.3557 | 90.99 | 3185 | 0.7433 | 0.3779 |
160
+ | 0.3563 | 91.99 | 3220 | 0.7249 | 0.3787 |
161
+ | 0.3304 | 92.99 | 3255 | 0.7543 | 0.3783 |
162
+ | 0.3596 | 93.99 | 3290 | 0.7329 | 0.3733 |
163
+ | 0.3548 | 94.99 | 3325 | 0.7531 | 0.3720 |
164
+ | 0.3269 | 95.99 | 3360 | 0.7377 | 0.3712 |
165
+ | 0.3289 | 96.99 | 3395 | 0.7378 | 0.3749 |
166
+ | 0.2978 | 97.99 | 3430 | 0.7200 | 0.3728 |
167
+ | 0.3075 | 98.99 | 3465 | 0.7210 | 0.3724 |
168
+ | 0.3402 | 99.99 | 3500 | 0.7173 | 0.3737 |
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