whisper-tiny-minds14-en-certificate
This model is a fine-tuned version of openai/whisper-tiny on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6246
- Wer: 29.5159
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: 16
- eval_batch_size: 8
- 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: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2722 | 3.4483 | 100 | 0.4924 | 29.9292 |
| 0.0480 | 6.8966 | 200 | 0.5424 | 29.8111 |
| 0.0070 | 10.3448 | 300 | 0.5973 | 29.6340 |
| 0.0026 | 13.7931 | 400 | 0.6194 | 29.6340 |
| 0.0021 | 17.2414 | 500 | 0.6246 | 29.5159 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2