Hugging Face's logo

gary109
/
ai-light-dance_drums_ft_pretrain_wav2vec2-base-new_onset-rbma13-2_7k

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
a1c9dbf
•
1 Parent(s): a0dd660

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-rbma13-2_7k
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-rbma13-2
18
+ split: train
19
+ args: onset-rbma13-2
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 1.0
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-rbma13-2_7k
30
+
31
+ This model is a fine-tuned version of [gary109/ai-light-dance_drums_pretrain_wav2vec2-base-new-7k](https://huggingface.co/gary109/ai-light-dance_drums_pretrain_wav2vec2-base-new-7k) on the ai_light_dance dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 3.2927
34
+ - Wer: 1.0
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
+ | No log | 1.0 | 1 | 68.1358 | 1.0 |
70
+ | No log | 2.0 | 2 | 68.1358 | 1.0 |
71
+ | No log | 3.0 | 3 | 68.1358 | 1.0 |
72
+ | No log | 4.0 | 4 | 68.0245 | 1.0 |
73
+ | No log | 5.0 | 5 | 67.7874 | 1.0 |
74
+ | No log | 6.0 | 6 | 67.4535 | 1.0 |
75
+ | No log | 7.0 | 7 | 67.0142 | 1.0 |
76
+ | No log | 8.0 | 8 | 67.0142 | 1.0 |
77
+ | No log | 9.0 | 9 | 66.4335 | 1.0 |
78
+ | 38.4011 | 10.0 | 10 | 65.7100 | 1.0 |
79
+ | 38.4011 | 11.0 | 11 | 64.8206 | 1.0 |
80
+ | 38.4011 | 12.0 | 12 | 63.8239 | 1.0 |
81
+ | 38.4011 | 13.0 | 13 | 62.6489 | 1.0 |
82
+ | 38.4011 | 14.0 | 14 | 61.3071 | 1.0 |
83
+ | 38.4011 | 15.0 | 15 | 59.7427 | 1.0 |
84
+ | 38.4011 | 16.0 | 16 | 58.0256 | 0.98 |
85
+ | 38.4011 | 17.0 | 17 | 56.0327 | 1.0 |
86
+ | 38.4011 | 18.0 | 18 | 53.7724 | 1.0 |
87
+ | 38.4011 | 19.0 | 19 | 51.2556 | 1.0 |
88
+ | 33.2554 | 20.0 | 20 | 48.4956 | 1.0 |
89
+ | 33.2554 | 21.0 | 21 | 45.4038 | 1.0 |
90
+ | 33.2554 | 22.0 | 22 | 41.9980 | 1.0 |
91
+ | 33.2554 | 23.0 | 23 | 41.9980 | 1.0 |
92
+ | 33.2554 | 24.0 | 24 | 38.2281 | 1.0 |
93
+ | 33.2554 | 25.0 | 25 | 34.1577 | 1.0 |
94
+ | 33.2554 | 26.0 | 26 | 29.7985 | 1.0 |
95
+ | 33.2554 | 27.0 | 27 | 25.1146 | 1.0 |
96
+ | 33.2554 | 28.0 | 28 | 20.2287 | 1.0 |
97
+ | 33.2554 | 29.0 | 29 | 15.3406 | 1.0 |
98
+ | 15.1206 | 30.0 | 30 | 10.7693 | 1.0 |
99
+ | 15.1206 | 31.0 | 31 | 6.8998 | 1.0 |
100
+ | 15.1206 | 32.0 | 32 | 4.5907 | 1.0 |
101
+ | 15.1206 | 33.0 | 33 | 3.3596 | 1.0 |
102
+ | 15.1206 | 34.0 | 34 | 2.7711 | 1.0 |
103
+ | 15.1206 | 35.0 | 35 | 2.5962 | 1.0 |
104
+ | 15.1206 | 36.0 | 36 | 2.9002 | 1.0 |
105
+ | 15.1206 | 37.0 | 37 | 3.0061 | 1.0 |
106
+ | 15.1206 | 38.0 | 38 | 2.8175 | 1.0 |
107
+ | 15.1206 | 39.0 | 39 | 2.4512 | 1.0 |
108
+ | 2.4298 | 40.0 | 40 | 2.3330 | 1.0 |
109
+ | 2.4298 | 41.0 | 41 | 2.3766 | 1.0 |
110
+ | 2.4298 | 42.0 | 42 | 2.5626 | 1.0 |
111
+ | 2.4298 | 43.0 | 43 | 2.9632 | 1.0 |
112
+ | 2.4298 | 44.0 | 44 | 3.2796 | 1.0 |
113
+ | 2.4298 | 45.0 | 45 | 3.4015 | 1.0 |
114
+ | 2.4298 | 46.0 | 46 | 3.2808 | 1.0 |
115
+ | 2.4298 | 47.0 | 47 | 3.2373 | 1.0 |
116
+ | 2.4298 | 48.0 | 48 | 3.2462 | 1.0 |
117
+ | 2.4298 | 49.0 | 49 | 3.6168 | 1.0 |
118
+ | 1.6143 | 50.0 | 50 | 3.6625 | 1.0 |
119
+ | 1.6143 | 51.0 | 51 | 3.7593 | 1.0 |
120
+ | 1.6143 | 52.0 | 52 | 3.9327 | 1.0 |
121
+ | 1.6143 | 53.0 | 53 | 3.7185 | 1.0 |
122
+ | 1.6143 | 54.0 | 54 | 3.9100 | 1.0 |
123
+ | 1.6143 | 55.0 | 55 | 4.3123 | 1.0 |
124
+ | 1.6143 | 56.0 | 56 | 4.2904 | 1.0 |
125
+ | 1.6143 | 57.0 | 57 | 3.9519 | 1.0 |
126
+ | 1.6143 | 58.0 | 58 | 3.4518 | 1.0 |
127
+ | 1.6143 | 59.0 | 59 | 3.0197 | 1.0 |
128
+ | 1.4054 | 60.0 | 60 | 2.8863 | 1.0 |
129
+ | 1.4054 | 61.0 | 61 | 2.9754 | 1.0 |
130
+ | 1.4054 | 62.0 | 62 | 3.2998 | 1.0 |
131
+ | 1.4054 | 63.0 | 63 | 3.8715 | 1.0 |
132
+ | 1.4054 | 64.0 | 64 | 4.1898 | 1.0 |
133
+ | 1.4054 | 65.0 | 65 | 4.1813 | 1.0 |
134
+ | 1.4054 | 66.0 | 66 | 3.9025 | 1.0 |
135
+ | 1.4054 | 67.0 | 67 | 3.4319 | 1.0 |
136
+ | 1.4054 | 68.0 | 68 | 3.2755 | 1.0 |
137
+ | 1.4054 | 69.0 | 69 | 3.3349 | 1.0 |
138
+ | 1.3121 | 70.0 | 70 | 3.5485 | 1.0 |
139
+ | 1.3121 | 71.0 | 71 | 3.9019 | 1.0 |
140
+ | 1.3121 | 72.0 | 72 | 4.0819 | 1.0 |
141
+ | 1.3121 | 73.0 | 73 | 3.9955 | 1.0 |
142
+ | 1.3121 | 74.0 | 74 | 3.7088 | 1.0 |
143
+ | 1.3121 | 75.0 | 75 | 3.2957 | 1.0 |
144
+ | 1.3121 | 76.0 | 76 | 3.1141 | 1.0 |
145
+ | 1.3121 | 77.0 | 77 | 3.0852 | 1.0 |
146
+ | 1.3121 | 78.0 | 78 | 3.1871 | 1.0 |
147
+ | 1.3121 | 79.0 | 79 | 3.4127 | 1.0 |
148
+ | 1.2576 | 80.0 | 80 | 3.6913 | 1.0 |
149
+ | 1.2576 | 81.0 | 81 | 3.8286 | 1.0 |
150
+ | 1.2576 | 82.0 | 82 | 3.8157 | 1.0 |
151
+ | 1.2576 | 83.0 | 83 | 3.6814 | 1.0 |
152
+ | 1.2576 | 84.0 | 84 | 3.4496 | 1.0 |
153
+ | 1.2576 | 85.0 | 85 | 3.2844 | 1.0 |
154
+ | 1.2576 | 86.0 | 86 | 3.2254 | 1.0 |
155
+ | 1.2576 | 87.0 | 87 | 3.2683 | 1.0 |
156
+ | 1.2576 | 88.0 | 88 | 3.3791 | 1.0 |
157
+ | 1.2576 | 89.0 | 89 | 3.5501 | 1.0 |
158
+ | 1.2373 | 90.0 | 90 | 3.6622 | 1.0 |
159
+ | 1.2373 | 91.0 | 91 | 3.7207 | 1.0 |
160
+ | 1.2373 | 92.0 | 92 | 3.6961 | 1.0 |
161
+ | 1.2373 | 93.0 | 93 | 3.6099 | 1.0 |
162
+ | 1.2373 | 94.0 | 94 | 3.5336 | 1.0 |
163
+ | 1.2373 | 95.0 | 95 | 3.4342 | 1.0 |
164
+ | 1.2373 | 96.0 | 96 | 3.3170 | 1.0 |
165
+ | 1.2373 | 97.0 | 97 | 3.2624 | 1.0 |
166
+ | 1.2373 | 98.0 | 98 | 3.2437 | 1.0 |
167
+ | 1.2373 | 99.0 | 99 | 3.2591 | 1.0 |
168
+ | 1.1952 | 100.0 | 100 | 3.2927 | 1.0 |
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