中文

Whisper Small Hi - Sanchit Gandhi

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

  • Loss: 0.4519
  • Wer: 32.0113

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: 500
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1011 2.44 1000 0.3075 34.6313
0.0264 4.89 2000 0.3558 33.1288
0.0025 7.33 3000 0.4214 32.5912
0.0006 9.78 4000 0.4519 32.0113
0.0002 12.22 5000 0.4679 32.0960

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.12.1
  • Datasets 2.5.3.dev0
  • Tokenizers 0.12.1