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: 0.4027
- Cer: 16.6588
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: 64
- eval_batch_size: 32
- 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: 3125
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.457 | 1.0 | 625 | 0.4558 | 19.5344 |
| 0.2711 | 2.0 | 1250 | 0.3992 | 18.0743 |
| 0.14 | 3.0 | 1875 | 0.3889 | 16.9447 |
| 0.0621 | 4.0 | 2500 | 0.3937 | 16.9491 |
| 0.0309 | 5.0 | 3125 | 0.4027 | 16.6588 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1