whisper-tiny-70-files
This model is a fine-tuned version of openai/whisper-tiny on the Speech Commands dataset. It achieves the following results on the evaluation set:
- Loss: 0.4202
- Accuracy: 0.8571
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
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1433 | 1.0 | 28 | 1.0751 | 0.2857 |
| 1.0581 | 2.0 | 56 | 0.9757 | 0.5714 |
| 0.7216 | 3.0 | 84 | 0.7070 | 0.5714 |
| 0.6422 | 4.0 | 112 | 0.6288 | 0.8571 |
| 0.395 | 5.0 | 140 | 0.5260 | 0.8571 |
| 0.1961 | 6.0 | 168 | 0.3009 | 1.0 |
| 0.2295 | 7.0 | 196 | 0.4961 | 0.8571 |
| 0.1916 | 8.0 | 224 | 0.4109 | 0.8571 |
| 0.1889 | 9.0 | 252 | 0.4259 | 0.8571 |
| 0.1485 | 10.0 | 280 | 0.4202 | 0.8571 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.2.2
- Datasets 3.2.0
- Tokenizers 0.21.0