whisper-large-v3-turbo-fa-c17-avs
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2583
- Wer: 27.2091
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: 200
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2293 | 0.4055 | 1000 | 0.4008 | 40.3172 |
| 0.167 | 0.8110 | 2000 | 0.3385 | 34.0503 |
| 0.0948 | 1.2165 | 3000 | 0.3067 | 31.7494 |
| 0.0669 | 1.6221 | 4000 | 0.2878 | 29.7909 |
| 0.0458 | 2.0276 | 5000 | 0.2583 | 27.2091 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1