openai/whisper-large
This model is a fine-tuned version of openai/whisper-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4047
- Wer: 11.5273
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: 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 |
|---|---|---|---|---|
| 0.5744 | 0.12 | 500 | 0.3488 | 14.3862 |
| 0.2143 | 1.02 | 1000 | 0.2956 | 12.6669 |
| 0.1776 | 1.15 | 1500 | 0.2892 | 11.5103 |
| 0.0562 | 2.04 | 2000 | 0.3257 | 11.8171 |
| 0.168 | 2.17 | 2500 | 0.3115 | 12.6878 |
| 0.0178 | 3.07 | 3000 | 0.3849 | 11.3784 |
| 0.0262 | 3.19 | 3500 | 0.3734 | 11.3523 |
| 0.0083 | 4.09 | 4000 | 0.4047 | 11.5273 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.9.1.dev0
- Tokenizers 0.13.2