exp2 / README.md
younghoonKIM's picture
End of training
b3896fa verified
metadata
language:
  - ko
license: apache-2.0
base_model: openai/whisper-large
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - younghoonKIM/MAICON2023_denoise_preprocessd
model-index:
  - name: whisper_large
    results: []

whisper_large

This model is a fine-tuned version of openai/whisper-large on the MAICON2023_denoise dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2852
  • Cer: 22.8829

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
  • 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 Cer
0.5697 0.36 1000 0.5593 37.0887
0.3805 0.71 2000 0.4014 30.2776
0.1647 1.07 3000 0.3255 26.6392
0.1244 1.43 4000 0.2852 22.8829

Framework versions

  • Transformers 4.37.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0