output_model_shunyalabs_data_base_model_40k
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6537
- Wer: 25.4320
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 4
- 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: 500
- training_steps: 40000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2530 | 3.9062 | 5000 | 0.7313 | 39.7873 |
| 0.0807 | 7.8125 | 10000 | 0.7854 | 38.2514 |
| 0.0304 | 11.7188 | 15000 | 0.7471 | 35.8293 |
| 0.0155 | 15.625 | 20000 | 0.7185 | 31.2805 |
| 0.0039 | 19.5312 | 25000 | 0.6875 | 28.7698 |
| 0.0008 | 23.4375 | 30000 | 0.6648 | 27.8541 |
| 0.0000 | 27.3438 | 35000 | 0.6559 | 25.7274 |
| 0.0000 | 31.25 | 40000 | 0.6537 | 25.4320 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- -