whisper-small-mupe-1.1
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8710
- Wer: 0.3844
- Cer: 0.5992
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: 2
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH 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
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.5858 | 1.0 | 500 | 0.8504 | 0.3993 | 0.6002 |
| 0.2313 | 2.0 | 1000 | 0.8907 | 0.3793 | 0.5986 |
| 0.1145 | 3.0 | 1500 | 0.9710 | 0.3898 | 0.6017 |
| 0.044 | 4.0 | 2000 | 1.0051 | 0.3987 | 0.5992 |
| 0.0259 | 5.0 | 2500 | 1.0740 | 0.4065 | 0.6015 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.7.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4