ft_model
This model is a fine-tuned version of openai/whisper-small on the EBRC dataset. It achieves the following results on the evaluation set:
- Loss: 0.3381
- Cer: 12.0280
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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 7500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.3783 | 1.0 | 1500 | 0.3772 | 15.4514 |
| 0.1885 | 2.0 | 3000 | 0.3377 | 14.1970 |
| 0.0896 | 3.0 | 4500 | 0.3270 | 13.0499 |
| 0.0379 | 4.0 | 6000 | 0.3331 | 12.6349 |
| 0.008 | 5.0 | 7500 | 0.3381 | 12.0280 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 7