whisper-medium-studio-records
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0328
- Wer: 15.6258
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: 1000
- training_steps: 6000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0573 | 0.4110 | 1000 | 0.0880 | 42.2742 |
| 0.0351 | 0.8220 | 2000 | 0.0619 | 31.4008 |
| 0.0149 | 1.2330 | 3000 | 0.0463 | 23.6377 |
| 0.0114 | 1.6441 | 4000 | 0.0358 | 18.2384 |
| 0.0036 | 2.0551 | 5000 | 0.0356 | 16.8201 |
| 0.0035 | 2.4661 | 6000 | 0.0328 | 15.6258 |
Framework versions
- Transformers 4.42.2
- Pytorch 2.1.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1