README.md

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: 68.94594978011065

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: 0.3617
• Wer: 68.9459

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1938	1.09	1000	0.2841	74.6631
0.0466	3.06	2000	0.2996	72.0953
0.005	5.04	3000	0.3376	70.4355
0.0021	7.01	4000	0.3617	68.9459
0.002	8.1	5000	0.3735	71.4711

Framework versions

• Transformers 4.26.0.dev0
• Pytorch 1.13.0+cu117
• Datasets 2.7.1.dev0
• Tokenizers 0.13.2