Hugging Face's logo

hyk000
/
bokji_ex

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
bokji_ex / README.md
hyk000's picture
hyk000
End of training
4a5c174 verified
preview code
|
raw
history blame contribute delete
1.63 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/bokji_ex
model-index:
  - name: bex_md
    results: []

bex_md

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

  • Loss: 2.8168
  • Cer: 89.6513

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: 0.01
  • 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: 1000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Cer
1.924 6.25 1000 2.8168 89.6513

Framework versions

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