<!-- 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. -->
whisper-medium-ft-GPT_2
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: 0.2050
- Wer: 16.5802
- Gpt: 8.8352
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Gpt |
|---|---|---|---|---|---|
| 0.6033 | 1.0 | 188 | 0.2203 | 22.8603 | 8.5556 |
| 0.116 | 2.0 | 376 | 0.1960 | 15.4966 | 8.7544 |
| 0.0392 | 3.0 | 564 | 0.1955 | 14.0854 | 8.9071 |
| 0.0155 | 4.0 | 752 | 0.2029 | 16.9373 | 8.7654 |
| 0.0052 | 5.0 | 940 | 0.2053 | 16.7842 | 8.6612 |
| 0.0015 | 6.0 | 1128 | 0.2050 | 16.5802 | 8.8352 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
