whisper-small-twi
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3872
- Wer: 73.3543
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: 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2865 | 2.2124 | 1000 | 1.1844 | 78.8981 |
| 0.1394 | 4.4248 | 2000 | 1.2766 | 78.3445 |
| 0.0944 | 6.6372 | 3000 | 1.3502 | 73.8312 |
| 0.0587 | 8.8496 | 4000 | 1.3872 | 73.3543 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Downloads last month
- 2