ko-address-whisper-small-5e-6

This model is a fine-tuned version of openai/whisper-small on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0484
• eval_cer: 0.9441
• eval_runtime: 3023.3682
• eval_samples_per_second: 3.842
• eval_steps_per_second: 0.24
• epoch: 0.4861
• step: 2000

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: 5e-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 8000
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.41.0.dev0
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1