<!-- 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-DS3K
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2673
- Wer: 11.3087
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 |
---|---|---|---|---|
0.5935 | 1.0 | 188 | 0.2777 | 12.4031 |
0.1145 | 2.0 | 376 | 0.2626 | 11.7191 |
0.0418 | 3.0 | 564 | 0.2595 | 11.6279 |
0.0155 | 4.0 | 752 | 0.2596 | 10.9895 |
0.0057 | 5.0 | 940 | 0.2690 | 11.0807 |
0.0019 | 6.0 | 1128 | 0.2673 | 11.3087 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cpu
- Datasets 2.12.0
- Tokenizers 0.13.3