中文

Whisper medium Sw2 - Kiazi Bora

This model is a fine-tuned version of openai/whisper-medium on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4788
  • Wer: 32.9689

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: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • 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
0.4257 0.43 1000 0.5451 36.7129
0.3494 0.87 2000 0.4788 32.9689

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu116
  • Datasets 2.7.1
  • Tokenizers 0.13.2