dgx1_whisper_small_finetune_teacher_babble_noise_mozilla_original_case_40_epochs_batch_8
This model is a fine-tuned version of openai/whisper-small.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5249
- Wer: 36.7485
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: 0.001
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 256
- total_train_batch_size: 2048
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 40
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.538 | 14.7 | 500 | 1.5291 | 39.0566 |
| 0.0037 | 29.41 | 1000 | 1.5249 | 36.7485 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1
- Datasets 2.8.0
- Tokenizers 0.13.2