korean-small_t33

This model is a fine-tuned version of openai/whisper-small on the korean_samll_dataset3 dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.1656
• eval_cer: 6.6580
• eval_runtime: 2081.9667
• eval_samples_per_second: 3.128
• eval_steps_per_second: 0.391
• step: 0

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
• num_epochs: 3.0
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2