metadata

language:
  - sv
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Swedish
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 11.0
          type: mozilla-foundation/common_voice_11_0
          config: sv-SE
          split: test
          args: 'config: sv, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 19.942996961630502

Whisper Small Swedish

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: 0.3442
Wer: 19.9430

Check here for the result of checkpoint-4000

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
training_steps: 4000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0+cu116
Datasets 2.7.1
Tokenizers 0.13.2