CheeLi03/whisper-tiny-ko-puct-4k

Whisper Tiny Korean Punctuation 4k - Chee Li

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

• Loss: 0.6823
• Wer: 39.8050

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: Use 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: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
0.121	6.2893	1000	0.5465	66.6667
0.0162	12.5786	2000	0.6224	44.8582
0.0069	18.8679	3000	0.6681	41.0461
0.0049	25.1572	4000	0.6823	39.8050

Framework versions

• Transformers 4.46.2
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.20.3