whisper-small-ha
This model is a fine-tuned version of openai/whisper-small on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2029
- Wer: 73.4456
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: 16
- eval_batch_size: 8
- 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
- training_steps: 100
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.5582 | 0.1592 | 25 | 3.2028 | 102.2384 |
| 2.4066 | 0.3185 | 50 | 1.9236 | 90.0899 |
| 1.4713 | 0.4777 | 75 | 1.4503 | 79.5102 |
| 1.1217 | 0.6369 | 100 | 1.2029 | 73.4456 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0