Whisper Tiny finetuned on MInDS-14
This model is a fine-tuned version of openai/whisper-tiny on the MInDS-14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5079
- Wer Ortho: 0.2825
- Wer: 0.2857
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: 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.2674 | 3.4483 | 100 | 0.5079 | 0.2825 | 0.2857 |
| 0.0332 | 6.8966 | 200 | 0.5782 | 0.3091 | 0.3129 |
| 0.0037 | 10.3448 | 300 | 0.6380 | 0.3029 | 0.3087 |
| 0.0010 | 13.7931 | 400 | 0.6747 | 0.3054 | 0.3093 |
| 0.0007 | 17.2414 | 500 | 0.6945 | 0.3128 | 0.3164 |
Framework versions
- Transformers 5.20.2
- Pytorch 2.11.0+cu130
- Datasets 3.6.0
- Tokenizers 0.23.3