whisper-tiny-minds-en
This model is a fine-tuned version of ihanif/whisper-tiny-minds-en on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 3.2762
- Wer Ortho: 0.9025
- Wer: 0.8878
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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 2.8469 | 0.04 | 1 | 3.2762 | 0.9025 | 0.8878 |
| 2.2255 | 0.07 | 2 | 3.2762 | 0.9025 | 0.8878 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3