Hugging Face's logo

vapari
/
wav2vec2-base-finetuned-gtzan

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
vapari commited on
Commit
026512a
•
1 Parent(s): f34209a

End of training

Browse files
Files changed (2) hide show
  1. README.md +23 -21
  2. model.safetensors +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.782051282051282
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.0679
37
- - Accuracy: 0.7821
38
 
39
  ## Model description
40
 
@@ -53,9 +53,9 @@ More information needed
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
- - learning_rate: 3e-05
57
- - train_batch_size: 10
58
- - eval_batch_size: 10
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
@@ -67,21 +67,23 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 2.0975 | 1.0 | 70 | 2.0767 | 0.3590 |
71
- | 1.6787 | 2.0 | 140 | 1.7150 | 0.4872 |
72
- | 1.5562 | 3.0 | 210 | 1.4839 | 0.4744 |
73
- | 1.2489 | 4.0 | 280 | 1.4014 | 0.6026 |
74
- | 0.9445 | 5.0 | 350 | 1.3975 | 0.5897 |
75
- | 0.8189 | 6.0 | 420 | 1.0886 | 0.7179 |
76
- | 0.6352 | 7.0 | 490 | 1.0411 | 0.6795 |
77
- | 0.6983 | 8.0 | 560 | 1.0652 | 0.6795 |
78
- | 0.4918 | 9.0 | 630 | 0.9020 | 0.7436 |
79
- | 0.534 | 10.0 | 700 | 1.1106 | 0.7308 |
80
- | 0.5065 | 11.0 | 770 | 0.8243 | 0.7821 |
81
- | 0.1966 | 12.0 | 840 | 1.0750 | 0.7436 |
82
- | 0.2377 | 13.0 | 910 | 1.0619 | 0.7564 |
83
- | 0.1434 | 14.0 | 980 | 1.1533 | 0.7436 |
84
- | 0.1128 | 15.0 | 1050 | 1.0679 | 0.7821 |
 
 
85
 
86
 
87
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.7866666666666666
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the GTZAN dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.2095
37
+ - Accuracy: 0.7867
38
 
39
  ## Model description
40
 
 
53
  ### Training hyperparameters
54
 
55
  The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 8
58
+ - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 2.0746 | 1.0 | 107 | 1.9697 | 0.46 |
71
+ | 1.5843 | 2.0 | 214 | 1.5908 | 0.5067 |
72
+ | 1.5982 | 3.0 | 321 | 1.4385 | 0.58 |
73
+ | 1.2855 | 4.0 | 428 | 1.3906 | 0.5467 |
74
+ | 1.0562 | 5.0 | 535 | 1.0173 | 0.7 |
75
+ | 0.8919 | 6.0 | 642 | 0.9564 | 0.6733 |
76
+ | 0.7214 | 7.0 | 749 | 0.8906 | 0.7467 |
77
+ | 0.7624 | 8.0 | 856 | 0.9580 | 0.7467 |
78
+ | 0.3619 | 9.0 | 963 | 1.0685 | 0.7733 |
79
+ | 0.3814 | 10.0 | 1070 | 1.1847 | 0.7467 |
80
+ | 0.4371 | 11.0 | 1177 | 0.9630 | 0.7867 |
81
+ | 0.3186 | 12.0 | 1284 | 0.9635 | 0.82 |
82
+ | 0.1474 | 13.0 | 1391 | 1.0021 | 0.8333 |
83
+ | 0.0918 | 14.0 | 1498 | 1.4497 | 0.7533 |
84
+ | 0.0592 | 15.0 | 1605 | 1.2592 | 0.7733 |
85
+ | 0.0084 | 16.0 | 1712 | 1.2656 | 0.7867 |
86
+ | 0.0216 | 17.0 | 1819 | 1.2095 | 0.7867 |
87
 
88
 
89
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a15412a55994e396fead6783a81f3a1471765fc149ed6c9b8c9a84660dd42572
3
  size 378310592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e5502d16c695f8064a6ca94b12922e8d20582120c830799856568be23243ed0
3
  size 378310592