---
language:
- ko
license: apache-2.0
base_model: openai/whisper-base
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- fleurs
metrics:
- wer
model-index:
- name: Whisper base Korean Punctuation 2k - Chee Li
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Google Fleurs
      type: fleurs
      config: ko_kr
      split: None
      args: 'config: ko split: test'
    metrics:
    - name: Wer
      type: wer
      value: 28.794326241134755
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Whisper base Korean Punctuation 2k - Chee Li

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Google Fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4727
- Wer: 28.7943

## 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: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer     |
|:-------------:|:-------:|:----:|:---------------:|:-------:|
| 0.039         | 6.2893  | 1000 | 0.4318          | 28.4043 |
| 0.0085        | 12.5786 | 2000 | 0.4727          | 28.7943 |


### Framework versions

- Transformers 4.43.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1