Whisper Small Eu - Lucia Urcelay
This model is a fine-tuned version of openai/whisper-small on the Basque subset of Common Voice 13 dataset, which contains 17509 audios and their corresponding transcriptions. It achieves the following results on the evaluation set:
- Loss: 0.3943
- Wer Ortho: 35.3856
- Wer: 28.3851
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: 500
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
|---|---|---|---|---|---|
| 0.3418 | 0.46 | 500 | 0.3943 | 35.3856 | 28.3851 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 1
Model tree for lurcelay/whisper-small-eu
Base model
openai/whisper-smallDataset used to train lurcelay/whisper-small-eu
Evaluation results
- Wer on Common Voice 13test set self-reported28.385