wosota-asr-medium-v1
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9563
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_FUSED 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: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5216 | 1.0546 | 1000 | 0.7874 |
| 0.1898 | 2.1092 | 2000 | 0.8209 |
| 0.0491 | 4.0184 | 3000 | 0.8889 |
| 0.0220 | 5.073 | 4000 | 0.9264 |
| 0.0051 | 6.1276 | 5000 | 0.9563 |
Framework versions
- Transformers 5.6.0.dev0
- Pytorch 2.10.0+cu128
- Datasets 2.16.0
- Tokenizers 0.22.2