metadata
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-tiny
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Whisper tiny AR - BH
results: []
Whisper tiny AR - BH
This model is a fine-tuned version of openai/whisper-tiny on the quran-ayat-speech-to-text dataset. It achieves the following results on the evaluation set:
- Loss: 0.0239
- Wer: 2.5045
- Cer: 1.3417
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: 5e-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.0573 | 1.0 | 469 | 0.0557 | 3.7557 | 1.5146 |
| 0.0363 | 2.0 | 938 | 0.0342 | 2.7052 | 1.2471 |
| 0.0255 | 3.0 | 1407 | 0.0278 | 2.5271 | 1.2806 |
| 0.0228 | 4.0 | 1876 | 0.0242 | 2.0662 | 1.1215 |
| 0.0173 | 5.0 | 2345 | 0.0223 | 2.6519 | 1.5182 |
| 0.0182 | 6.0 | 2814 | 0.0211 | 2.5336 | 1.3413 |
| 0.02 | 7.0 | 3283 | 0.0203 | 2.5506 | 1.3904 |
| 0.0146 | 8.0 | 3752 | 0.0197 | 2.1023 | 1.1479 |
| 0.0132 | 9.0 | 4221 | 0.0191 | 2.4327 | 1.3539 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0