metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-tiny
tags:
  - generated_from_trainer
datasets:
  - ubulut/quran-verses
metrics:
  - wer
model-index:
  - name: Whisper Tiny AR - Quran
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: quran-whisper-dataset
          type: ubulut/quran-verses
          config: default
          split: None
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 85.61643835616438

Whisper Tiny AR - Quran

This model is a fine-tuned version of openai/whisper-tiny on the quran-whisper-dataset dataset. It achieves the following results on the evaluation set:

Loss: 3.8268
Wer: 85.6164

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: 0.0001
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.0067	17.2414	1000	2.9626	87.5
0.0022	34.4828	2000	3.5443	87.5856
0.0	51.7241	3000	3.7999	85.6164
0.0	68.9655	4000	3.8268	85.6164

Framework versions

Transformers 4.42.3
Pytorch 2.3.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1