pazarf
This model is a fine-tuned version of microsoft/paza-whisper-large-v3-turbo on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2344
- Wer: 16.13
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: 48
- eval_batch_size: 8
- 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: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2272 | 1.1521 | 500 | 0.2548 | 16.87 |
| 0.1874 | 2.3041 | 1000 | 0.2391 | 16.16 |
| 0.1728 | 3.4562 | 1500 | 0.2353 | 16.09 |
| 0.1692 | 4.6083 | 2000 | 0.2344 | 16.13 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 4
Model tree for EzekielMW/pazarf
Base model
openai/whisper-large-v3 Finetuned
openai/whisper-large-v3-turbo Finetuned
microsoft/paza-whisper-large-v3-turbo