Hugging Face's logo

hyk000
/
repo_name

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
repo_name / README.md
hyk000's picture
hyk000
End of training
eacc191 verified
preview code
|
raw
history blame
1.81 kB
metadata
library_name: transformers
language:
  - ko
license: apache-2.0
base_model: openai/whisper-base
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - hyk000/phonekor
model-index:
  - name: korpw
    results: []

korpw

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

  • Loss: 0.5903
  • Cer: 18.4448

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 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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
0.0341 10.0 1000 0.4909 70.6834
0.0021 20.0 2000 0.5542 18.7048
0.0008 30.0 3000 0.5810 18.7454
0.0007 40.0 4000 0.5903 18.4448

Framework versions

  • Transformers 4.47.0.dev0
  • Pytorch 2.5.0
  • Datasets 3.0.2
  • Tokenizers 0.20.1