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: 0.0088
- Wer: 0.1392
- Cer: 0.0529
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: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.0087 | 1.0 | 313 | 0.0090 | 0.1752 | 0.0620 |
| 0.0069 | 2.0 | 626 | 0.0088 | 0.1385 | 0.0468 |
| 0.007 | 3.0 | 939 | 0.0087 | 0.1595 | 0.0576 |
| 0.0052 | 4.0 | 1252 | 0.0088 | 0.1329 | 0.0420 |
| 0.0055 | 5.0 | 1565 | 0.0086 | 0.1571 | 0.0525 |
| 0.004 | 6.0 | 1878 | 0.0086 | 0.1609 | 0.0575 |
| 0.0034 | 7.0 | 2191 | 0.0089 | 0.1372 | 0.0447 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0