MohammedNasri/whisper-Large-ar

Whisper Large ar - MohammedNasri

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

• Loss: 0.2872
• Wer: 24.8545

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: 1
• 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: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.3129	0.03	1000	0.3643	31.2737
0.3197	0.05	2000	0.2872	24.8545

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.7.0
• Tokenizers 0.13.2