<!-- 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. -->
888aatt
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0831
- Wer: 44.8577
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 3000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0732 | 0.18 | 500 | 0.2005 | 31.2302 |
| 0.048 | 0.36 | 1000 | 0.1672 | 20.4939 |
| 0.0624 | 0.54 | 1500 | 0.1348 | 50.5496 |
| 0.0797 | 0.72 | 2000 | 0.1061 | 33.1727 |
| 0.0551 | 0.9 | 2500 | 0.0894 | 37.4191 |
| 0.0144 | 1.08 | 3000 | 0.0831 | 44.8577 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
