whisper-base-no-specific-topic
This model is a fine-tuned version of openai/whisper-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3753
- Wer: 20.4545
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: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use 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: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4753 | 1.0535 | 1000 | 0.3846 | 21.3450 |
| 0.0845 | 2.107 | 2000 | 0.3753 | 20.4545 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 3
Model tree for wwwtwwwt/whisper-base-compare-case
Base model
openai/whisper-base