Whisper base uz - AbdulxoliqMirzaev

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

  • Loss: 0.2568
  • Wer: 26.1656

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 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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.5844 0.5714 500 0.5611 48.8804
0.2606 1.1429 1000 0.3306 32.4540
0.2337 1.7143 1500 0.2756 27.9908
0.1468 2.2857 2000 0.2568 26.1656

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.5.1+cu121
  • Datasets 3.3.1
  • Tokenizers 0.21.0
Downloads last month
22
Safetensors
Model size
72.6M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for AbdulxoliqMirzaev/whisper-uz

Finetuned
(438)
this model