whisper-small-ablation-add-NLD-80
This model is a fine-tuned version of openai/whisper-small on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 0.4274
- Wer: 17.0206
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3531 | 0.4673 | 200 | 0.4262 | 18.9012 |
| 0.2799 | 0.9346 | 400 | 0.4623 | 18.4440 |
| 0.1829 | 1.4019 | 600 | 0.4345 | 18.7094 |
| 0.1841 | 1.8692 | 800 | 0.4215 | 17.1976 |
| 0.091 | 2.3364 | 1000 | 0.4274 | 17.0206 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.11.0+cu130
- Datasets 3.0.1
- Tokenizers 0.20.0