Edit model card

Whisper Small Fa - BuzzyBuzzy

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: 0.4491
  • Wer: 34.8008

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: 10000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0929 0.86 2000 0.3911 38.2279
0.0594 1.72 4000 0.3968 37.6368
0.0222 2.58 6000 0.4174 38.7857
0.0082 3.44 8000 0.4417 35.8512
0.0026 4.3 10000 0.4491 34.8008

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
13
Hosted inference API
or or
This model can be loaded on the Inference API on-demand.

Dataset used to train taesiri/whisper-small-fa-2

Evaluation results