metadata
language:
- ar
license: apache-2.0
base_model: tarteel-ai/whisper-base-ar-quran
tags:
- generated_from_trainer
datasets:
- zolfa
metrics:
- wer
model-index:
- name: Whisper-raghadomar
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Zolfa Dataset
type: zolfa
args: 'config: ar, split: test'
metrics:
- name: Wer
type: wer
value: 10.344827586206897
Whisper-raghadomar
This model is a fine-tuned version of tarteel-ai/whisper-base-ar-quran on the Zolfa Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0293
- Wer: 10.3448
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: 16
- 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: 5
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.0006 | 4.7619 | 100 | 0.0060 | 6.8966 |
| 0.0004 | 9.5238 | 200 | 0.0233 | 10.3448 |
| 0.0004 | 14.2857 | 300 | 0.0199 | 10.3448 |
| 0.0002 | 19.0476 | 400 | 0.0309 | 10.3448 |
| 0.0004 | 23.8095 | 500 | 0.0253 | 10.3448 |
| 0.0002 | 28.5714 | 600 | 0.0284 | 10.3448 |
| 0.0002 | 33.3333 | 700 | 0.0275 | 10.3448 |
| 0.0002 | 38.0952 | 800 | 0.0301 | 10.3448 |
| 0.0001 | 42.8571 | 900 | 0.0286 | 10.3448 |
| 0.0001 | 47.6190 | 1000 | 0.0293 | 10.3448 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1