Dovud-Asadov/whisper-uzbek-stt-local

Whisper Large Uzbek Local

This model is a fine-tuned version of openai/whisper-large-v3 on the Local Uzbek Speech Dataset dataset. It achieves the following results on the evaluation set:

• Loss: 2.2590
• Wer: 113.4642

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
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 16
• total_eval_batch_size: 16
• 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: 50
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
1.2738	16.6667	100	2.2590	113.4642

Framework versions

• Transformers 4.56.0
• Pytorch 2.8.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.0