---
language:
- ko
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: Whisper Korean - whisper-medium
  results: []
---

<!-- 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 Korean - whisper-medium

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3709
- Cer: 8.6970

## 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: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Cer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.0045        | 11.1111 | 500  | 0.3555          | 8.8374 |
| 0.0006        | 22.2222 | 1000 | 0.3709          | 8.6970 |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1