Hugging Face's logo

fierce74
/
wav2vec2-base-finetuned-gtzan

Audio Classification
Transformers
Safetensors
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
fierce74 commited on
Commit
2c3b6ae
·
verified ·
1 Parent(s): 9fa9cf6

End of training

Browse files
Files changed (2) hide show
  1. README.md +18 -16
  2. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.86
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: 0.5107
37
- - Accuracy: 0.86
38
 
39
  ## Model description
40
 
@@ -60,23 +60,25 @@ The following hyperparameters were used during training:
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 10
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 1.9043 | 1.0 | 113 | 1.8057 | 0.46 |
71
- | 1.2603 | 2.0 | 226 | 1.3549 | 0.58 |
72
- | 1.1442 | 3.0 | 339 | 1.0001 | 0.68 |
73
- | 0.6053 | 4.0 | 452 | 0.9841 | 0.68 |
74
- | 0.5621 | 5.0 | 565 | 0.9519 | 0.69 |
75
- | 0.541 | 6.0 | 678 | 0.6576 | 0.79 |
76
- | 0.3868 | 7.0 | 791 | 0.4867 | 0.86 |
77
- | 0.1518 | 8.0 | 904 | 0.5443 | 0.84 |
78
- | 0.1699 | 9.0 | 1017 | 0.4024 | 0.91 |
79
- | 0.093 | 10.0 | 1130 | 0.5107 | 0.86 |
 
 
80
 
81
 
82
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.87
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: 0.5916
37
+ - Accuracy: 0.87
38
 
39
  ## Model description
40
 
 
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
  - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 12
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
69
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
70
+ | 1.9043 | 1.0 | 113 | 0.46 | 1.8057 |
71
+ | 1.2603 | 2.0 | 226 | 0.58 | 1.3549 |
72
+ | 1.1442 | 3.0 | 339 | 0.68 | 1.0001 |
73
+ | 0.6053 | 4.0 | 452 | 0.68 | 0.9841 |
74
+ | 0.5621 | 5.0 | 565 | 0.69 | 0.9519 |
75
+ | 0.541 | 6.0 | 678 | 0.79 | 0.6576 |
76
+ | 0.3868 | 7.0 | 791 | 0.86 | 0.4867 |
77
+ | 0.1518 | 8.0 | 904 | 0.84 | 0.5443 |
78
+ | 0.1699 | 9.0 | 1017 | 0.91 | 0.4024 |
79
+ | 0.0798 | 10.0 | 1130 | 0.5878 | 0.86 |
80
+ | 0.1869 | 11.0 | 1243 | 0.6483 | 0.86 |
81
+ | 0.1439 | 12.0 | 1356 | 0.5916 | 0.87 |
82
 
83
 
84
  ### Framework versions
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5592fc0411a5f5bf2892bad86dcd359a59958a00d168ea0439f38300c7df441
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702f74a72844722eea0202bc43598d0447d49de8883310a979f9b2ce252ff263
3
  size 5368