whisper-small-fc-am
This model is a fine-tuned version of wu-kiot/whisper-small-am-fleurs on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3756
- Wer: 62.7306
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- 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: 150
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2866 | 1.0 | 44 | 0.2855 | 63.9958 |
| 0.1582 | 2.0 | 88 | 0.2958 | 64.1539 |
| 0.0885 | 3.0 | 132 | 0.3311 | 67.4222 |
| 0.0793 | 4.0 | 176 | 0.3700 | 66.4207 |
| 0.0375 | 5.0 | 220 | 0.3756 | 62.7306 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0