ahmedlh/whisper-tiny-en_v4

Whisper tiny En v4 Naji

This model is a fine-tuned version of openai/whisper-tiny on the Common Voice 1 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5576
• Wer Ortho: 33.2416
• Wer: 24.7805

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: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant_with_warmup
• lr_scheduler_warmup_steps: 50
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.2724	0.4119	250	0.5662	34.0042	25.3767
0.2531	0.8237	500	0.5576	33.2416	24.7805

Framework versions

• Transformers 4.52.4
• Pytorch 2.7.0+cu128
• Datasets 2.14.6
• Tokenizers 0.21.1