---
language:
- ko
license: apache-2.0
tags:
- hf-asr-leaderboard
- generated_from_trainer
base_model: openai/whisper-base
datasets:
- 0603_15000_freetalk_matched
model-index:
- name: baseWhisper_finetune
  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. -->

# baseWhisper_finetune

This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the gingercake01/0603_15000_freetalk_matched dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3428
- Cer: 7.9820

## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 20

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Cer    |
|:-------------:|:-------:|:----:|:---------------:|:------:|
| 0.0836        | 5.3333  | 1000 | 0.2870          | 8.1564 |
| 0.0068        | 10.6667 | 2000 | 0.3203          | 7.9067 |
| 0.0026        | 16.0    | 3000 | 0.3428          | 7.9820 |


### Framework versions

- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1