Whisper whisper-large-v3-turbo zul
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the dsfsi-anv/za-african-next-voices dataset. It achieves the following results on the evaluation set:
- Loss: 0.3028
- Wer: 21.7553
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: 64
- eval_batch_size: 64
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4397 | 0.2 | 200 | 0.4422 | 32.3634 |
| 0.3516 | 0.4 | 400 | 0.3710 | 27.0171 |
| 0.3005 | 1.135 | 600 | 0.3342 | 23.8024 |
| 0.2317 | 1.335 | 800 | 0.3125 | 22.9160 |
| 0.2232 | 2.07 | 1000 | 0.3028 | 21.7553 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.4