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: 0.5153
- Accuracy: 0.88
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: 8
- eval_batch_size: 8
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.0258 | 1.0 | 113 | 1.7851 | 0.47 |
1.5568 | 2.0 | 226 | 1.4525 | 0.48 |
0.9996 | 3.0 | 339 | 1.3081 | 0.56 |
0.9843 | 4.0 | 452 | 0.8743 | 0.81 |
0.5038 | 5.0 | 565 | 0.7456 | 0.8 |
0.5988 | 6.0 | 678 | 0.6650 | 0.82 |
0.5372 | 7.0 | 791 | 0.7010 | 0.8 |
0.2489 | 8.0 | 904 | 0.5241 | 0.87 |
0.2511 | 9.0 | 1017 | 0.4765 | 0.89 |
0.0771 | 10.0 | 1130 | 0.5153 | 0.88 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.0
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for ziblets/wav2vec2-base-finetuned-gtzan
Base model
facebook/wav2vec2-base