metadata
library_name: transformers
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-ar-private
results: []
whisper-ar-private
This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3115
- Wer: 36.1533
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: 32
- 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: 500
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3798 | 0.7855 | 2000 | 0.3634 | 44.2367 |
| 0.2557 | 1.5711 | 4000 | 0.3220 | 39.4150 |
| 0.1723 | 2.3566 | 6000 | 0.3103 | 37.1623 |
| 0.1172 | 3.1422 | 8000 | 0.3125 | 36.7185 |
| 0.113 | 3.9277 | 10000 | 0.3115 | 36.1533 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1