noflm
update model card README.md
fd5b912
metadata
language:
  - ja
license: other
tags:
  - whisper-event
  - generated_from_trainer
datasets:
  - Elite35P-Server/EliteVoiceProject
metrics:
  - wer
model-index:
  - name: Whisper Base Japanese Elite
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Elite35P-Server/EliteVoiceProject twitter
          type: Elite35P-Server/EliteVoiceProject
          config: twitter
          split: test
          args: twitter
        metrics:
          - name: Wer
            type: wer
            value: 17.073170731707318

Whisper Base Japanese Elite

This model is a fine-tuned version of openai/whisper-base on the Elite35P-Server/EliteVoiceProject twitter dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4385
  • Wer: 17.0732

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: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: constant_with_warmup
  • lr_scheduler_warmup_steps: 200
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0002 111.0 1000 0.2155 9.7561
0.0001 222.0 2000 0.2448 12.1951
0.0 333.0 3000 0.2674 13.4146
0.0 444.0 4000 0.2943 15.8537
0.0 555.0 5000 0.3182 17.0732
0.0 666.0 6000 0.3501 18.9024
0.0 777.0 7000 0.3732 16.4634
0.0 888.0 8000 0.4025 17.0732
0.0 999.0 9000 0.4178 20.1220
0.0 1111.0 10000 0.4385 17.0732

Framework versions

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