Zakryah/whisper-medium

Whisper Medium - Zakryah

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.2773
• Wer: 56.0556

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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
0.5683	0.3299	1000	0.5194	39.9527
0.3317	0.6598	2000	0.2859	59.6546
0.2961	0.9898	3000	0.2791	56.6892
0.2619	1.3197	4000	0.2773	56.0556

Framework versions

• PEFT 0.14.1.dev0
• Transformers 4.50.0.dev0
• Pytorch 2.6.0+cu126
• Datasets 3.3.2
• Tokenizers 0.21.0