whisper-tiny-ko / README.md
Rifky's picture
update model card README.md
3f883d9
|
raw
history blame
1.31 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: whisper-tiny-ko
    results: []

whisper-tiny-ko

This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 2.4594
  • Wer: 60.2614

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-06
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 1

Training results

Training Loss Epoch Step Validation Loss Wer
2.6045 0.04 1 2.4594 60.2614

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cpu
  • Datasets 2.12.0
  • Tokenizers 0.13.3