whisper-medium.en-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-medium.en on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.2836
- Accuracy: 0.94
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.0049 | 1.0 | 112 | 0.9562 | 0.62 |
0.4197 | 2.0 | 225 | 0.4341 | 0.85 |
0.3768 | 3.0 | 337 | 0.3772 | 0.89 |
0.0268 | 4.0 | 450 | 0.4503 | 0.92 |
0.0028 | 4.98 | 560 | 0.2836 | 0.94 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 6
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.