Edit model card

Whisper Small Dutch

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

  • Loss: 0.2035
  • Wer: 11.5135

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: 112
  • eval_batch_size: 56
  • 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: 500
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
8
Safetensors
Model size
242M params
Tensor type
F32
·

Finetuned from

Dataset used to train pplantinga/whisper-small-nl

Evaluation results