noflm's picture
Update README.md
432d5c0
metadata
language:
  - ja
license: apache-2.0
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_11_0
metrics:
  - wer
model-index:
  - name: Whisper Small Japanese
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: mozilla-foundation/common_voice_11_0 ja
          type: mozilla-foundation/common_voice_11_0
          config: ja
          split: test
          args: ja
        metrics:
          - name: Wer
            type: wer
            value: 13.326167779676846

Whisper Small Japanese

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

  • Loss: 0.4317
  • Wer: 13.3262

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: constant_with_warmup
  • lr_scheduler_warmup_steps: 500
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.042 3.03 2000 0.3056 12.9174
0.0085 7.01 4000 0.3752 13.1746
0.0047 10.04 6000 0.4103 13.5817
0.0042 14.01 8000 0.4202 13.5323
0.0051 17.05 10000 0.4317 13.3262

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.8.1.dev0
  • Tokenizers 0.13.2