Whisper ESP-ENG - EDGEN AI
This model is a fine-tuned version of destil-whisper/whisper-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1444
- Wer: 5.0507
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: 10
- 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 | Wer |
|---|---|---|---|---|
| 0.1036 | 2.86 | 1000 | 0.1841 | 9.0986 |
| 0.0147 | 5.71 | 2000 | 0.1459 | 5.7878 |
| 0.0039 | 8.57 | 3000 | 0.1451 | 5.5099 |
| 0.001 | 11.43 | 4000 | 0.1444 | 5.0507 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2
- Downloads last month
- 1