metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-gabriel_fold_2
results: []
whisper-medium-gabriel_fold_2
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: 0.2478
- Wer: 10.8141
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 |
|---|---|---|---|---|
| 0.7153 | 1.0 | 169 | 0.2548 | 12.0595 |
| 0.1204 | 2.0 | 338 | 0.2332 | 10.9964 |
| 0.0427 | 3.0 | 507 | 0.2359 | 10.3888 |
| 0.0157 | 4.0 | 676 | 0.2386 | 10.8445 |
| 0.0052 | 5.0 | 845 | 0.2454 | 10.8748 |
| 0.002 | 6.0 | 1014 | 0.2478 | 10.8141 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3