whisper-small-ablation-add-NLD-90
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: 0.4254
- Wer: 17.5811
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 |
|---|---|---|---|---|
| 0.2897 | 0.5263 | 200 | 0.4269 | 18.6726 |
| 0.177 | 1.0526 | 400 | 0.4194 | 18.0826 |
| 0.1516 | 1.5789 | 600 | 0.4377 | 17.9720 |
| 0.0713 | 2.1053 | 800 | 0.4025 | 17.8319 |
| 0.074 | 2.6316 | 1000 | 0.4254 | 17.5811 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.11.0+cu130
- Datasets 3.0.1
- Tokenizers 0.20.0