Whisper Medium Galician
This model is a fine-tuned version of openai/whisper-medium on the google/fleurs gl_es dataset. It achieves the following results on the evaluation set:
- Loss: 0.4553
- Wer: 14.6741
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0002 | 39.01 | 1000 | 0.4553 | 14.6741 |
| 0.0001 | 79.0 | 2000 | 0.5023 | 14.9400 |
| 0.0 | 119.0 | 3000 | 0.5317 | 15.1609 |
| 0.0 | 159.0 | 4000 | 0.5513 | 15.2015 |
| 0.0 | 199.0 | 5000 | 0.5593 | 15.2060 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2
- Downloads last month
- 8
Dataset used to train geninhu/whisper-medium-gl-fleurs
Evaluation results
- Wer on google/fleurs gl_estest set self-reported14.674