Hugging Face's logo

nomnoos37
/
stt-turbo-1225-v1.1

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
stt-turbo-1225-v1.1 / README.md
nomnoos37's picture
nomnoos37
End of training
50ba16c verified
preview code
|
raw
history blame contribute delete
1.82 kB
metadata
library_name: transformers
language:
  - ko
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: Whisper Small ko
    results: []

Whisper Small ko

This model is a fine-tuned version of openai/whisper-large-v3-turbo on the custom dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0021
  • Wer: 0.2425

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: 4e-05
  • train_batch_size: 64
  • eval_batch_size: 64
  • 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: 100
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
0.0336 1.4706 100 0.1071 12.0453
0.0207 2.9412 200 0.0394 5.6589
0.0073 4.4118 300 0.0257 2.8294
0.0038 5.8824 400 0.0066 0.8892
0.0008 7.3529 500 0.0021 0.2425

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0