haseong8012's picture
Create README.md
3d01162
|
raw
history blame
1.07 kB
metadata
language:
  - ko
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - haseong8012/child-50k
model-index:
  - name: whisper-small_child-50k2
    results: []
metrics:
  - wer
  - cer

whisper-small-fineTuned_By_korean-child-command-voice_train-0-10000_smaplingRate-16000-aag-test1

This model is a fine-tuned version of openai/whisper-small on the haseong8012/child-50k dataset.

  • eval_loss: 0.01577906496822834
  • eval_cer: 0.5696816412724527
  • eval_wer: 1.2814293799013663

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:

Framework versions