Whisper Small en - bika
This model is a fine-tuned version of openai/whisper-small on the pfedrx dataset. It achieves the following results on the evaluation set:
- Loss: 0.8296
- Wer: 13.8889
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: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0001 | 1000.0 | 1000 | 0.7543 | 13.8889 |
| 0.0 | 2000.0 | 2000 | 0.8129 | 13.8889 |
| 0.0 | 3000.0 | 3000 | 0.8296 | 13.8889 |
Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for bika5/output
Base model
openai/whisper-small