metadata

language:
  - ar
license: apache-2.0
base_model: openai/whisper-base
tags:
  - ar-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_15_0
metrics:
  - wer
model-index:
  - name: Whisper base ar - spongebob
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 15.0
          type: mozilla-foundation/common_voice_15_0
          args: 'config: ar, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 43.07405356570396

Whisper base ar - spongebob

This model is a fine-tuned version of openai/whisper-base on the Common Voice 15.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.4649
Wer: 43.0741

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: 2
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 1500
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.4268	0.87	500	0.5523	50.5668
0.2877	1.73	1000	0.4752	45.1258
0.2197	2.6	1500	0.4649	43.0741

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.0