whisper-medium-LoRA_nosie_aug
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: 0.7758
- Wer: 37.4880
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.534 | 1.0 | 188 | 2.7617 | 32.7900 |
| 2.0348 | 2.0 | 376 | 1.6089 | 28.4756 |
| 0.9957 | 3.0 | 564 | 0.8496 | 27.8044 |
| 0.7184 | 4.0 | 752 | 0.7912 | 38.0633 |
| 0.6808 | 5.0 | 940 | 0.7758 | 37.4880 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
Model tree for adityarra07/whisper-med-LoRA_nosie_128_64_3k
Base model
openai/whisper-medium