whisper-small-english-finetuned
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1440
- Wer: 3.8983
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.0433 | 0.1 | 100 | 0.3707 | 4.6501 |
| 0.4545 | 0.2 | 200 | 0.1443 | 4.4088 |
| 0.4759 | 0.3 | 300 | 0.1370 | 3.9911 |
| 0.1712 | 1.088 | 400 | 0.1346 | 3.9168 |
| 0.1130 | 1.188 | 500 | 0.1413 | 3.9818 |
| 0.1500 | 1.288 | 600 | 0.1400 | 3.8890 |
| 0.0810 | 2.076 | 700 | 0.1392 | 3.8704 |
| 0.0750 | 2.176 | 800 | 0.1457 | 3.9818 |
| 0.0667 | 2.276 | 900 | 0.1428 | 3.8333 |
| 0.0437 | 3.064 | 1000 | 0.1440 | 3.8983 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2