Edit model card

Whisper Small Czech CV11

This model is a fine-tuned version of openai/whisper-small on the mozilla-foundation/common_voice_11_0 cs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3587
  • Wer: 18.5557

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: 64
  • eval_batch_size: 32
  • 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
0.0392 4.01 1000 0.2857 19.6675
0.0028 8.02 2000 0.3204 18.3495
0.0011 12.03 3000 0.3402 18.5336
0.0008 16.04 4000 0.3537 18.4563
0.0007 21.01 5000 0.3587 18.5557

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
28

Finetuned from

Dataset used to train mikr/whisper-small-cs-cv11

Evaluation results