---
language:
- ko
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- Marcusxx/chungnamFireStation3Kfiles
metrics:
- wer
model-index:
- name: chungnam_firestation3Kfiles_WER_model
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: Marcusxx/chungnamFireStation3Kfiles
      type: Marcusxx/chungnamFireStation3Kfiles
      args: 'config: ko, split: valid'
    metrics:
    - type: wer
      value: 59.73084886128365
      name: Wer
---

<!-- 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. -->

# chungnam_firestation3Kfiles_WER_model

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Marcusxx/chungnamFireStation3Kfiles dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9083
- Wer: 59.7308

## 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: 100
- training_steps: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Wer      |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| 0.4191        | 1.6667  | 250  | 0.6137          | 146.0663 |
| 0.0955        | 3.3333  | 500  | 0.6744          | 62.7329  |
| 0.048         | 5.0     | 750  | 0.6991          | 101.6563 |
| 0.0279        | 6.6667  | 1000 | 0.7719          | 60.4555  |
| 0.0106        | 8.3333  | 1250 | 0.8092          | 63.7681  |
| 0.0083        | 10.0    | 1500 | 0.7876          | 66.6667  |
| 0.0056        | 11.6667 | 1750 | 0.8225          | 60.2484  |
| 0.0007        | 13.3333 | 2000 | 0.8544          | 60.0414  |
| 0.0004        | 15.0    | 2250 | 0.8616          | 58.1781  |
| 0.0003        | 16.6667 | 2500 | 0.8729          | 57.4534  |
| 0.0002        | 18.3333 | 2750 | 0.8832          | 58.0745  |
| 0.0002        | 20.0    | 3000 | 0.8920          | 58.5921  |
| 0.0002        | 21.6667 | 3250 | 0.8984          | 59.4203  |
| 0.0002        | 23.3333 | 3500 | 0.9029          | 59.3168  |
| 0.0002        | 25.0    | 3750 | 0.9070          | 59.6273  |
| 0.0002        | 26.6667 | 4000 | 0.9083          | 59.7308  |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.2.2+cu121
- Datasets 3.2.0
- Tokenizers 0.19.1