---
language:
- kr
license: apache-2.0
base_model: openai/whisper-base
tags:
- generated_from_trainer
model-index:
- name: Fine-tuning 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. -->

# Fine-tuning whisper

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0042
- Cer: 0.0

## 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: 10
- training_steps: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 4.2772        | 0.28  | 5    | 4.1382          | 173.1771 |
| 4.1353        | 0.56  | 10   | 3.2786          | 104.9479 |
| 2.5873        | 0.83  | 15   | 1.6016          | 47.3958  |
| 1.0092        | 1.11  | 20   | 0.6032          | 22.9167  |
| 0.3746        | 1.39  | 25   | 0.3756          | 16.1458  |
| 0.0944        | 1.67  | 30   | 0.1149          | 7.8125   |
| 0.0215        | 1.94  | 35   | 0.0449          | 2.6042   |
| 0.0038        | 2.22  | 40   | 0.0180          | 1.8229   |
| 0.0013        | 2.5   | 45   | 0.0118          | 0.7812   |
| 0.0011        | 2.78  | 50   | 0.0101          | 0.7812   |
| 0.0004        | 3.06  | 55   | 0.0081          | 0.2604   |
| 0.0003        | 3.33  | 60   | 0.0068          | 0.2604   |
| 0.0003        | 3.61  | 65   | 0.0058          | 0.2604   |
| 0.0002        | 3.89  | 70   | 0.0052          | 0.0      |
| 0.0002        | 4.17  | 75   | 0.0048          | 0.0      |
| 0.0002        | 4.44  | 80   | 0.0045          | 0.0      |
| 0.0002        | 4.72  | 85   | 0.0044          | 0.0      |
| 0.0002        | 5.0   | 90   | 0.0043          | 0.0      |
| 0.0002        | 5.28  | 95   | 0.0043          | 0.0      |
| 0.0002        | 5.56  | 100  | 0.0042          | 0.0      |


### Framework versions

- Transformers 4.36.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0