whisper-turbo-v1
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4562
- Wer: 20.2373
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: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4073 | 1.0 | 218 | 0.3949 | 24.1977 |
| 0.3204 | 2.0 | 436 | 0.3502 | 21.8300 |
| 0.2274 | 3.0 | 654 | 0.3457 | 21.0923 |
| 0.1631 | 4.0 | 872 | 0.3478 | 20.9801 |
| 0.1222 | 5.0 | 1090 | 0.3724 | 20.7217 |
| 0.0869 | 6.0 | 1308 | 0.3843 | 21.3574 |
| 0.0596 | 7.0 | 1526 | 0.4061 | 20.4209 |
| 0.0433 | 8.0 | 1744 | 0.4194 | 20.5313 |
| 0.0262 | 9.0 | 1962 | 0.4410 | 20.3121 |
| 0.0204 | 10.0 | 2180 | 0.4562 | 20.2373 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Downloads last month
- 3