Edit model card

whisper-tiny-hi

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

  • Loss: 0.7990
  • Wer: 43.8869

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
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 3000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.1747 7.02 1000 0.5674 41.6800
0.0466 14.03 2000 0.7042 43.7378
0.0174 22.0 3000 0.7990 43.8869

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.10.0
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
8

Dataset used to train amitkayal/whisper-tiny-hi

Space using amitkayal/whisper-tiny-hi 1

Evaluation results