metadata

language:
  - ja
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_16_1
metrics:
  - wer
model-index:
  - name: whisper-large-v3-japanese-4k-steps
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: Common Voice 16.1
          type: mozilla-foundation/common_voice_16_1
          config: ja
          split: None
          args: 'config: ja, split: test'
        metrics:
          - name: Wer
            type: wer
            value: 1821.4909443725744

whisper-large-v3-japanese-4k-steps

This model is a fine-tuned version of openai/whisper-large-v3 on the Common Voice 16.1 dataset. I followed a post by Sanchit Gandhi, https://huggingface.co/blog/fine-tune-whisper It took 24 hours using an A100 on Google Colab to complete 4000 steps using the Common Voice 16.1 dataset. Training loss dropped over epochs but validation loss increased, so textbook overfitting. Furthermore, WER increased. It achieves the following results on the evaluation set:

Loss: 0.4057
Wer: 18.2149

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: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
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: 4000
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1374	1.02	1000	0.3618	11.983182
0.0508	2.04	2000	0.3658	17.554657
0.0206	3.05	3000	0.3904	21.087484
0.0066	4.07	4000	0.4057	18.214909

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2