DeathCover1003/whisper-tiny_to_japanese_accent

Whisper tiny Japanese

This model is a fine-tuned version of openai/whisper-tiny on the Japanese English dataset. It achieves the following results on the evaluation set:

• Loss: 0.4626
• Wer: 21.4912

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: 2
• eval_batch_size: 1
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.1373	1.2438	1000	0.4816	22.1178
0.09	2.4876	2000	0.4626	21.4912

Framework versions

• Transformers 4.50.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0