<!-- 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 - Swedish
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4326
- Wer: 27.5604
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2166 | 1.3 | 1000 | 0.4678 | 32.2067 |
| 0.0991 | 2.59 | 2000 | 0.4459 | 29.0581 |
| 0.0462 | 3.89 | 3000 | 0.4326 | 27.5604 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
