Hugging Face's logo

dupa888
/
whisper-small-kor

Automatic Speech Recognition
Transformers
PyTorch
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Community
whisper-small-kor / README.md
dupa888's picture
dupa888
End of training
40a1b87
preview code
|
raw
history blame contribute delete
1.43 kB
metadata
language:
  - ko
license: apache-2.0
base_model: openai/whisper-small
tags:
  - hf-asr-leaderboard
  - generated_from_trainer
datasets:
  - Bingsu/KSS_Dataset
model-index:
  - name: Whisper Small ko - dup8888
    results: []

Whisper Small ko - dup8888

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

  • eval_loss: 0.6954
  • eval_cer: 214.7267
  • eval_runtime: 939.4252
  • eval_samples_per_second: 1.066
  • eval_steps_per_second: 0.134
  • epoch: 2.0
  • step: 1000

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: 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

Framework versions

  • Transformers 4.35.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1