metadata
library_name: transformers
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-pato-16
results: []
whisper-pato-16
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2622
- Wer: 18.7245
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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1200
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4191 | 1.0 | 7571 | 0.4169 | 35.9921 |
| 0.2812 | 2.0 | 15142 | 0.3270 | 30.7195 |
| 0.1381 | 3.0 | 22713 | 0.2948 | 24.3961 |
| 0.0485 | 4.0 | 30284 | 0.2677 | 21.0149 |
| 0.0088 | 5.0 | 37855 | 0.2622 | 18.7245 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.0