---
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- hyojin99/EBRC
base_model: openai/whisper-base
model-index:
- name: ft_model
  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. -->

# ft_model

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the EBRC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4271
- Cer: 19.8362

## 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: 50
- training_steps: 6000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.5853        | 0.4   | 1000 | 0.5518          | 34.2215 |
| 0.4595        | 0.8   | 2000 | 0.4852          | 23.2105 |
| 0.313         | 1.2   | 3000 | 0.4593          | 21.0304 |
| 0.327         | 1.6   | 4000 | 0.4400          | 21.5894 |
| 0.311         | 2.0   | 5000 | 0.4277          | 19.6565 |
| 0.2514        | 2.4   | 6000 | 0.4271          | 19.8362 |


### Framework versions

- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2