Whisper tiny American English
This model is a fine-tuned version of openai/whisper-tiny on the American English dataset. It achieves the following results on the evaluation set:
- Loss: 0.2330
- Wer: 9.6880
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: 3.75e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1804 | 1.4925 | 100 | 0.1988 | 8.8605 |
| 0.1055 | 2.9851 | 200 | 0.2086 | 9.5328 |
| 0.0442 | 4.4776 | 300 | 0.2140 | 9.5846 |
| 0.0307 | 5.9701 | 400 | 0.2135 | 9.1708 |
| 0.0225 | 7.4627 | 500 | 0.2230 | 9.6018 |
| 0.0214 | 8.9552 | 600 | 0.2225 | 9.8259 |
| 0.0157 | 10.4478 | 700 | 0.2265 | 9.8259 |
| 0.0167 | 11.9403 | 800 | 0.2272 | 9.6880 |
| 0.0139 | 13.4328 | 900 | 0.2309 | 9.7225 |
| 0.0141 | 14.9254 | 1000 | 0.2330 | 9.6880 |
Framework versions
- Transformers 5.23.0.dev0
- Pytorch 2.11.0+cu130
- Datasets 5.1.0
- Tokenizers 0.23.3