whisper-large-v2-finetuned-gtzan
This model is a fine-tuned version of openai/whisper-large-v2 on the GTZAN dataset. It achieves the following results on the evaluation set:
- Loss: 0.7142
- Accuracy: 0.9
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- 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 |
---|---|---|---|---|
2.0464 | 1.0 | 449 | 1.6761 | 0.42 |
0.9369 | 2.0 | 899 | 1.0398 | 0.74 |
1.0591 | 3.0 | 1348 | 1.0710 | 0.78 |
0.0632 | 4.0 | 1798 | 0.6605 | 0.86 |
0.0022 | 5.0 | 2247 | 1.0940 | 0.82 |
0.0004 | 6.0 | 2697 | 0.7089 | 0.92 |
0.0004 | 7.0 | 3146 | 0.6176 | 0.92 |
0.0005 | 8.0 | 3596 | 0.6688 | 0.9 |
0.0002 | 9.0 | 4045 | 0.7052 | 0.9 |
0.0002 | 9.99 | 4490 | 0.7142 | 0.9 |
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.