whisper-tiny-id
This model is a fine-tuned version of openai/whisper-tiny on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.3803
- Wer: 28.8415
- Cer: 12.5724
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- 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: 500
- training_steps: 5180
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.5575 | 1.0998 | 1036 | 0.4486 | 33.2331 | 13.9213 |
| 0.2442 | 3.0994 | 2072 | 0.3947 | 31.0158 | 13.2855 |
| 0.1124 | 5.0990 | 3108 | 0.3859 | 28.6954 | 12.5669 |
| 0.0643 | 7.0986 | 4144 | 0.3859 | 28.9618 | 13.1445 |
| 0.0456 | 9.0983 | 5180 | 0.3803 | 28.8415 | 12.5724 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2