Whisper Small Western Frisian (Netherlands)

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

  • Loss: 0.5703
  • Wer: 21.8466

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
0.0078 10.01 1000 0.5184 23.0973
0.0009 21.0 2000 0.5653 22.5434
0.0007 31.01 3000 0.5703 21.8466
0.0004 42.0 4000 0.5968 21.9574
0.0003 52.01 5000 0.6044 22.0360

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.0+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2
Downloads last month
16
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train polixonrio/whisper-small-fy-NL-Transfer-From-English

Evaluation results