metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_0
metrics:
  - wer
model-index:
  - name: Whisper Small ar - majed test
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.0
          type: mozilla-foundation/common_voice_16_0
          config: ar
          split: test
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 260.25560867966163

Whisper Small ar - majed test

This model is a fine-tuned version of openai/whisper-small on the Common Voice 16.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.3249
Wer: 260.2556

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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3013	0.41	1000	0.4102	337.6793
0.2533	0.82	2000	0.3525	344.5476
0.1632	1.24	3000	0.3397	278.4185
0.1526	1.65	4000	0.3249	260.2556

Framework versions

Transformers 4.36.2
Pytorch 2.1.2
Datasets 2.16.1
Tokenizers 0.15.0