<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
whisper-large-v2-es-v2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3020
- Wer: 29.8958
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 4000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0262 | 0.33 | 500 | 0.3233 | 30.1042 |
| 0.0917 | 0.65 | 1000 | 0.2680 | 34.4792 |
| 0.1301 | 0.98 | 1500 | 0.2704 | 28.3333 |
| 0.0276 | 1.31 | 2000 | 0.2779 | 33.125 |
| 0.0275 | 1.63 | 2500 | 0.2893 | 28.2292 |
| 0.0232 | 1.96 | 3000 | 0.3061 | 35.0 |
| 0.0204 | 2.29 | 3500 | 0.3044 | 30.5208 |
| 0.0128 | 2.61 | 4000 | 0.3020 | 29.8958 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.14.0
