<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
ft_model
This model is a fine-tuned version of openai/whisper-base on the important dataset. It achieves the following results on the evaluation set:
- Loss: 1.0252
- Cer: 36.9125
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.5019 | 2.81 | 1000 | 0.8572 | 69.8151 |
| 0.1416 | 5.62 | 2000 | 0.9210 | 41.5237 |
| 0.0244 | 8.43 | 3000 | 0.9906 | 37.2912 |
| 0.0139 | 11.24 | 4000 | 1.0252 | 36.9125 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
