whisper-es-multicorpus-streaming-v3
This model is a fine-tuned version of openai/whisper-small on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.0816
- Wer: 0.0628
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1346 | 0.2 | 200 | 0.1566 | 0.2221 |
| 0.117 | 0.4 | 400 | 0.1217 | 0.0790 |
| 0.0861 | 0.6 | 600 | 0.1079 | 0.0633 |
| 0.0419 | 1.1180 | 800 | 0.1172 | 0.0899 |
| 0.0467 | 1.318 | 1000 | 0.0816 | 0.0628 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1