whisper-small.en
This model is a fine-tuned version of crossdelenna/whisper-small.en on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0004
- Wer: 0.7672
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: 10
- training_steps: 1401
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0047 | 1.03 | 400 | 0.0037 | 0.9334 |
| 0.0033 | 2.06 | 800 | 0.0012 | 0.7416 |
| 0.0011 | 3.09 | 1200 | 0.0004 | 0.7672 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2