---
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
base_model: openai/whisper-base
datasets:
- Drunk/aihub_sample
model-index:
- name: tuning_test_whisper
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/drunkjin/huggingface/runs/wa7gys7i)
# tuning_test_whisper

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the aihub_sample dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2301
- Cer: 18.4549

## 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: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer     |
|:-------------:|:------:|:----:|:---------------:|:-------:|
| 0.0001        | 500.0  | 1000 | 1.0798          | 18.0258 |
| 0.0001        | 1000.0 | 2000 | 1.1747          | 18.4549 |
| 0.0           | 1500.0 | 3000 | 1.2109          | 18.4549 |
| 0.0           | 2000.0 | 4000 | 1.2301          | 18.4549 |


### Framework versions

- Transformers 4.42.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.19.1
- Tokenizers 0.19.1