Edit model card

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: 0.4297
  • Wer: 53.2422

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0876 2.44 1000 0.2914 34.9107
0.0203 4.89 2000 0.3453 40.8702
0.0016 7.33 3000 0.4042 46.0298
0.0005 9.78 4000 0.4297 53.2422

Framework versions

  • Transformers 4.28.0.dev0
  • Pytorch 1.13.1+cu116
  • Datasets 2.10.1
  • Tokenizers 0.13.2
Downloads last month
2

Dataset used to train me2140733/whisper-small-hi

Evaluation results