<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Whisper Small sv-SE NST - Lab 2
This model is a fine-tuned version of openai/whisper-small on the NST Swedish ASR dataset. It achieves the following results on the evaluation set:
- Loss: 0.1305
- Wer: 10.1678
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1635 | 0.67 | 1000 | 0.1694 | 13.4993 |
| 0.07 | 1.33 | 2000 | 0.1431 | 11.3802 |
| 0.0597 | 2.0 | 3000 | 0.1302 | 10.4682 |
| 0.0193 | 2.67 | 4000 | 0.1305 | 10.1678 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
