Zakryah/whisper-turbo

Whisper Turbo - Zakryah

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1877
• Wer: 20.5468

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
0.1926	0.3299	1000	0.1996	20.9454
0.2061	0.6598	2000	0.1913	20.7485
0.188	0.9898	3000	0.1887	20.7962
0.1832	1.3197	4000	0.1877	20.5468

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