Hugging Face's logo

youngisk
/
whisper-small-ko_Moon

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
whisper-small-ko_Moon / README.md
youngisk's picture
youngisk
End of training
1805acf verified
preview code
|
raw history blame contribute delete
No virus
1.65 kB
metadata
language:
  - ko
license: apache-2.0
base_model: openai/whisper-small
tags:
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_12_0
model-index:
  - name: Whisper Small Ko
    results: []

Whisper Small Ko

This model is a fine-tuned version of openai/whisper-small on the Common Voice 12.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5311
  • Cer: 13.0489

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: 2
  • 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

Training results

Training Loss Epoch Step Validation Loss Cer
0.0002 16.1290 1000 0.4759 12.5471
0.0001 32.2581 2000 0.5073 13.0489
0.0001 48.3871 3000 0.5246 13.0489
0.0 64.5161 4000 0.5311 13.0489

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1