<!-- 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-es
This model is a fine-tuned version of Jack200133/whisper-large-v2-es on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2507
- Wer: 33.2292
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: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.06 | 0.16 | 250 | 0.3232 | 30.9375 |
| 0.0974 | 0.33 | 500 | 0.3196 | 30.8333 |
| 0.1453 | 0.49 | 750 | 0.2780 | 25.4167 |
| 0.1655 | 0.65 | 1000 | 0.2616 | 32.8125 |
| 0.1342 | 0.82 | 1250 | 0.2526 | 28.3333 |
| 0.1568 | 0.98 | 1500 | 0.2489 | 31.6667 |
| 0.0806 | 1.14 | 1750 | 0.2541 | 35.8333 |
| 0.045 | 1.31 | 2000 | 0.2507 | 33.2292 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1
