metadata

library_name: transformers
language:
  - ko
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: Whisper turbo KO - GTH
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 17.0
          type: mozilla-foundation/common_voice_17_0
          config: ko
          split: None
          args: 'config: ko, split: test'
        metrics:
          - type: wer
            value: 27.00534759358289
            name: Wer

Whisper turbo KO - GTH

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the Common Voice 17.0 dataset. It achieves the following results on the evaluation set:

Loss: 0.5105
Wer: 27.0053

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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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
0.0087	22.2222	1000	0.4786	30.3667
0.0014	44.4444	2000	0.4935	30.7105
0.0001	66.6667	3000	0.5067	27.0817
0.0001	88.8889	4000	0.5105	27.0053

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu124
Datasets 3.1.0
Tokenizers 0.20.3