seastar105's picture
update model card README.md
faedbf5
|
raw
history blame
2.19 kB
metadata
language:
  - ko
license: apache-2.0
tags:
  - hf-asr-leaderboard
  - whisper-event
  - generated_from_trainer
datasets:
  - kresnik/zeroth_korean
metrics:
  - wer
model-index:
  - name: Whisper Medium 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: 3.6440295136274656

Whisper Medium Korean

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

  • Loss: 0.0727
  • Wer: 3.6440
  • Cer: 1.4840

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: 5e-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_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: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer Cer
0.0873 0.72 1000 0.1086 7.7549 2.5597
0.0258 1.44 2000 0.0805 4.5475 1.7588
0.0091 2.16 3000 0.0719 3.7946 1.5664
0.0086 2.88 4000 0.0704 3.5537 1.5232
0.0019 3.59 5000 0.0727 3.6440 1.4840

Framework versions

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