ft_model
This model is a fine-tuned version of openai/whisper-base on the EBRC dataset. It achieves the following results on the evaluation set:
- Loss: 0.4181
- Cer: 15.8554
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 |
|---|---|---|---|---|
| 0.4744 | 1.0 | 1250 | 0.4683 | 20.8493 |
| 0.24 | 2.0 | 2500 | 0.4053 | 18.0384 |
| 0.1392 | 3.0 | 3750 | 0.3982 | 17.4262 |
| 0.0664 | 4.0 | 5000 | 0.4042 | 16.7622 |
| 0.0273 | 5.0 | 6250 | 0.4119 | 16.3872 |
| 0.0096 | 6.0 | 7500 | 0.4181 | 15.8554 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 4