<!-- 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-B16-E6-DS31K
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: 0.1274
- Wer: 6.2948
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 |
|---|---|---|---|---|
| 0.1892 | 1.0 | 1954 | 0.1137 | 7.3350 |
| 0.0608 | 2.0 | 3908 | 0.1044 | 11.1191 |
| 0.026 | 3.0 | 5862 | 0.1133 | 6.7073 |
| 0.0097 | 4.0 | 7816 | 0.1173 | 6.4562 |
| 0.0031 | 5.0 | 9770 | 0.1215 | 6.5997 |
| 0.0008 | 6.0 | 11724 | 0.1274 | 6.2948 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
