metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-medium-gabriel_fold_4
results: []
whisper-medium-gabriel_fold_4
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: 0.2132
- Wer: 9.6024
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 |
|---|---|---|---|---|
| 0.6975 | 1.0 | 169 | 0.2328 | 24.6539 |
| 0.1201 | 2.0 | 338 | 0.1991 | 10.1031 |
| 0.0441 | 3.0 | 507 | 0.2071 | 9.8969 |
| 0.0173 | 4.0 | 676 | 0.2069 | 9.7202 |
| 0.0056 | 5.0 | 845 | 0.2120 | 9.8675 |
| 0.0018 | 6.0 | 1014 | 0.2132 | 9.6024 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3