wsper
This model is a fine-tuned version of openai/whisper-tiny on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1823
- Wer: 48.9699
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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: 50
- training_steps: 120
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.5079 | 4.0 | 60 | 1.3599 | 80.9826 |
| 0.4908 | 8.0 | 120 | 1.1823 | 48.9699 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 2
Model tree for hzraslan/wsper
Base model
openai/whisper-tiny