metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-medium
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Medium Arabic - Mostafa Khedr
    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: 38.02222018180149

Whisper Medium Arabic - Mostafa Khedr

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

Loss: 0.2691
Wer: 38.0222

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: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2453	0.4156	1000	0.3289	42.9602
0.2326	0.8313	2000	0.2976	42.0990
0.139	1.2469	3000	0.2883	41.0376
0.1081	1.6625	4000	0.2720	39.0763
0.0543	2.0781	5000	0.2691	38.0222

Framework versions

Transformers 4.43.3
Pytorch 2.4.1+cu121
Datasets 3.1.0
Tokenizers 0.19.1