<!-- 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-czech
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: 0.3164
- Wer: 13.1258
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 |
|---|---|---|---|---|
| 0.3982 | 1.0 | 789 | 0.2601 | 14.0344 |
| 0.1299 | 2.0 | 1578 | 0.2536 | 13.8218 |
| 0.0548 | 3.0 | 2367 | 0.2645 | 13.4158 |
| 0.0182 | 4.0 | 3156 | 0.2984 | 13.1065 |
| 0.005 | 5.0 | 3945 | 0.3164 | 13.1258 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
