egemenakdeniz/whisper-medium-tr

Whisper medium tr -

This model is a fine-tuned version of openai/whisper-medium on the commonvoice_17_tr_fixed dataset. It achieves the following results on the evaluation set:

• Loss: 0.1808
• Wer: 16.0497

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 5000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.2742	0.1509	1000	0.2717	22.4456
0.195	0.3018	2000	0.2356	19.7325
0.1529	0.4528	3000	0.2173	18.3296
0.1535	0.6037	4000	0.1933	16.9751
0.1671	0.7546	5000	0.1808	16.0497

Framework versions

• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1