Hugging Face's logo

Rrezearta
/
whisper-fine-tuned

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Macedonian
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community

Whisper Small MK

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

  • Loss: 0.2558
  • Wer: 13.3623

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • 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: 300
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0071 5.8140 1000 0.2528 14.4269
0.0005 11.6279 2000 0.2558 13.3623

Framework versions

  • Transformers 5.1.0
  • Pytorch 2.9.0+cu126
  • Datasets 4.5.0
  • Tokenizers 0.22.2
Downloads last month
3
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
Automatic Speech Recognition
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Rrezearta/whisper-fine-tuned

Base model

openai/whisper-small
Finetuned
(3586)
this model

Dataset used to train Rrezearta/whisper-fine-tuned

Evaluation results