---
language:
- ko
license: apache-2.0
base_model: openai/whisper-large
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- younghoonKIM/MAICON2023_denoise_preprocessd
model-index:
- name: whisper_large
  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_large

This model is a fine-tuned version of [openai/whisper-large](https://huggingface.co/openai/whisper-large) on the MAICON2023_denoise dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2852
- Cer: 22.8829

## 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: 4
- 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: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.5697        | 0.36  | 1000 | 0.5593          | 37.0887 |
| 0.3805        | 0.71  | 2000 | 0.4014          | 30.2776 |
| 0.1647        | 1.07  | 3000 | 0.3255          | 26.6392 |
| 0.1244        | 1.43  | 4000 | 0.2852          | 22.8829 |


### Framework versions

- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0