whisper-small-mupe-2
This model is a fine-tuned version of lejonck/whisper-small-mupe-1.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6868
- Wer: 0.3057
- Cer: 0.5581
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 |
|---|---|---|---|---|---|
| 0.4614 | 1.0 | 750 | 0.6909 | 0.3057 | 0.5575 |
| 0.1668 | 2.0 | 1500 | 0.7257 | 0.3790 | 0.5736 |
| 0.0468 | 3.0 | 2250 | 0.8084 | 0.3491 | 0.5667 |
| 0.0269 | 4.0 | 3000 | 0.8183 | 0.3567 | 0.5660 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.7.0+cu126
- Datasets 4.0.0
- Tokenizers 0.21.4