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: 1.5989
  • Wer: 83.4696

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: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0005 15.87 1000 1.5989 83.4696

Framework versions

  • Transformers 4.25.0.dev0
  • Pytorch 1.12.1+cu113
  • Datasets 2.7.0
  • Tokenizers 0.13.2
Downloads last month
29
Hosted inference API
or or
This model can be loaded on the Inference API on-demand.

Dataset used to train arbml/whisper-tiny-ar

Evaluation results