jarvis-whisper-small
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6699
- Wer: 23.188
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.7220 | 5.5755 | 100 | 2.5188 | 109.058 |
| 4.4316 | 11.1151 | 200 | 0.6531 | 23.913 |
| 0.0738 | 16.6906 | 300 | 0.6283 | 21.377 |
| 0.0052 | 22.2302 | 400 | 0.6671 | 23.188 |
| 0.0005 | 27.8058 | 500 | 0.6699 | 23.188 |
Framework versions
- Transformers 5.12.1
- Pytorch 2.11.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2