mustafoyev202/whisper-uz-adv

Whisper Medium Uzbek

This model is a fine-tuned version of mustafoyev202/whisper-uz on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.7319

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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: 2000

Training results

Training Loss	Epoch	Step	Validation Loss
0.7933	0.8	500	0.9289
0.678	1.6	1000	0.8336
0.6008	2.4	1500	0.7544
0.6056	3.2	2000	0.7319

Framework versions

• PEFT 0.15.2.dev0
• Transformers 4.51.0.dev0
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1