metadata

language:
  - ko
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
  - whisper-event
datasets:
  - kresnik/zeroth_korean
metrics:
  - wer
model-index:
  - name: Whisper Small Korean
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Zeroth Korean
          type: kresnik/zeroth_korean
          config: clean
          split: test
          args: 'split: test'
        metrics:
          - name: Wer
            type: wer
            value: 6.761029965366662

Whisper Small Korean

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

Loss: 0.0899
Wer: 6.7610

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: 8
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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1277	0.72	1000	0.1489	12.2271
0.0379	1.44	2000	0.1053	6.7159
0.0138	2.16	3000	0.0918	6.0382
0.0141	2.87	4000	0.0899	6.7610

Framework versions

Transformers 4.26.0.dev0
Pytorch 1.13.0a0+d0d6b1f
Datasets 2.7.1
Tokenizers 0.13.2