metadata

library_name: transformers
language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: whisper-small-arabic-nouraa5
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: ar
          split: None
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 72.8198859005705

whisper-small-arabic-nouraa5

This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

Loss: 2.8401
Wer: 72.8199

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Use OptimizerNames.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: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
2.3611	1.0	15	3.5182	65.0367
2.1002	2.0	30	3.1825	69.9674
1.9664	2.8533	42	2.8401	72.8199

Framework versions

Transformers 4.51.1
Pytorch 2.6.0+cu124
Datasets 3.5.0
Tokenizers 0.21.1