---
language:
- ko
license: apache-2.0
tags:
- generated_from_trainer
base_model: openai/whisper-base
datasets:
- AIHub/noise
model-index:
- name: Whisper Base Noise Ko - Dearlie
  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 Base Noise Ko - Dearlie

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Noise Data dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9216
- Cer: 37.5124

## 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: 0.0001
- 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: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 1.3536        | 0.8780 | 1000 | 1.3752          | 55.5864 |
| 0.944         | 1.7559 | 2000 | 1.0808          | 51.4185 |
| 0.5985        | 2.6339 | 3000 | 0.9612          | 40.2651 |
| 0.3207        | 3.5119 | 4000 | 0.9216          | 37.5124 |


### Framework versions

- Transformers 4.41.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1