<!-- 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. -->
openai/whisper-base.en
This model is a fine-tuned version of openai/whisper-base.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1913
- Wer: 3.9530
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: 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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0489 | 10.0 | 500 | 0.1624 | 8.5536 |
| 0.0019 | 20.0 | 1000 | 0.1682 | 4.0051 |
| 0.0007 | 30.01 | 1500 | 0.1782 | 4.1167 |
| 0.0004 | 40.01 | 2000 | 0.1823 | 4.0497 |
| 0.0003 | 51.0 | 2500 | 0.1861 | 3.9827 |
| 0.0002 | 61.0 | 3000 | 0.1888 | 3.9753 |
| 0.0002 | 71.01 | 3500 | 0.1907 | 3.9678 |
| 0.0002 | 81.01 | 4000 | 0.1913 | 3.9530 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2
