wav2vec2-base-finetuned-gtzan
This model is a fine-tuned version of facebook/wav2vec2-base on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.6713
- Accuracy: 0.83
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.9059 | 1.0 | 90 | 1.7870 | 0.48 |
1.4224 | 2.0 | 180 | 1.3290 | 0.67 |
1.2667 | 3.0 | 270 | 1.2726 | 0.57 |
0.791 | 4.0 | 360 | 1.0556 | 0.7 |
0.6727 | 5.0 | 450 | 0.7369 | 0.8 |
0.4685 | 6.0 | 540 | 0.6371 | 0.86 |
0.5113 | 7.0 | 630 | 0.8083 | 0.79 |
0.2758 | 8.0 | 720 | 0.5974 | 0.87 |
0.1834 | 9.0 | 810 | 0.5047 | 0.88 |
0.1746 | 10.0 | 900 | 0.6713 | 0.83 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 8
Model tree for kenzic/wav2vec2-base-finetuned-gtzan
Base model
facebook/wav2vec2-base