metadata
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: whisper-small-persian
results: []
whisper-small-persian
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8237
- Wer: 62.5
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: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.89 | 2 | 5.1135 | 87.5 |
| No log | 1.78 | 4 | 3.1980 | 75.0 |
| No log | 2.67 | 6 | 2.5434 | 75.0 |
| No log | 4.0 | 9 | 1.8864 | 62.5 |
| No log | 4.44 | 10 | 1.8237 | 62.5 |
Framework versions
- Transformers 4.35.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1