Whisper Base Jyutping without Tones Full Version

This model is a fine-tuned version of openai/whisper-base on the Common Voice 14.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0839
  • Wer: 10.3370

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 400
  • training_steps: 2400

Training results

Training Loss Epoch Step Validation Loss Wer
0.122 0.18 800 0.1265 11.7520
0.0979 0.35 1600 0.0946 9.8493
0.0843 0.53 2400 0.0839 10.3370

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1
  • Datasets 2.14.5
  • Tokenizers 0.13.3