<!-- 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-10000
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: 0.1989
- Wer: 59.7961
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 |
|---|---|---|---|---|
| 0.3909 | 1.0 | 625 | 0.1901 | 32.0479 |
| 0.0935 | 2.0 | 1250 | 0.1800 | 85.0621 |
| 0.0364 | 3.0 | 1875 | 0.1858 | 19.3706 |
| 0.0125 | 4.0 | 2500 | 0.1905 | 41.4450 |
| 0.004 | 5.0 | 3125 | 0.1969 | 86.5248 |
| 0.0012 | 6.0 | 3750 | 0.1989 | 59.7961 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
