metadata
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
model-index:
- name: Whisper-medium-Arabic-phoneme-5
results: []
Whisper-medium-Arabic-phoneme-5
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2774
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 21 | 1.7386 |
| 2.7841 | 2.0 | 42 | 0.3929 |
| 0.4966 | 3.0 | 63 | 0.3452 |
| 0.0748 | 4.0 | 84 | 0.3248 |
| 0.0616 | 5.0 | 105 | 0.2732 |
| 0.0339 | 6.0 | 126 | 0.2862 |
| 0.0339 | 7.0 | 147 | 0.2728 |
| 0.0128 | 8.0 | 168 | 0.2729 |
| 0.0048 | 9.0 | 189 | 0.2764 |
| 0.0022 | 10.0 | 210 | 0.2774 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0