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: 0.5537
- 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 |
|---|---|---|---|---|
| 1.7898 | 1.0 | 113 | 1.8052 | 0.45 |
| 1.4297 | 2.0 | 226 | 1.2229 | 0.62 |
| 1.041 | 3.0 | 339 | 0.9934 | 0.65 |
| 1.3882 | 4.0 | 452 | 1.1735 | 0.62 |
| 0.7248 | 5.0 | 565 | 0.8461 | 0.69 |
| 0.6128 | 6.0 | 678 | 0.7391 | 0.75 |
| 0.3225 | 7.0 | 791 | 0.8754 | 0.74 |
| 0.6483 | 8.0 | 904 | 0.8341 | 0.79 |
| 0.2755 | 9.0 | 1017 | 0.5537 | 0.88 |
| 0.4398 | 10.0 | 1130 | 0.6076 | 0.85 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.