---
language:
- hi
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- aihub_elder
model-index:
- name: whisper-small-ko-E50_Yfreq-SA
  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-small-ko-E50_Yfreq-SA

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the aihub elder over 70 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1687
- Cer: 4.7169

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.4395        | 0.13  | 100  | 0.2828          | 6.6494 |
| 0.2892        | 0.26  | 200  | 0.2139          | 6.1971 |
| 0.2647        | 0.39  | 300  | 0.2029          | 6.4673 |
| 0.2371        | 0.52  | 400  | 0.1935          | 5.5569 |
| 0.2442        | 0.64  | 500  | 0.1884          | 5.3513 |
| 0.2419        | 0.77  | 600  | 0.1828          | 5.3102 |
| 0.2159        | 0.9   | 700  | 0.1848          | 5.2103 |
| 0.1394        | 1.03  | 800  | 0.1771          | 5.1281 |
| 0.1337        | 1.16  | 900  | 0.1799          | 5.2925 |
| 0.1458        | 1.29  | 1000 | 0.1787          | 4.9283 |
| 0.1306        | 1.42  | 1100 | 0.1787          | 4.8637 |
| 0.1211        | 1.55  | 1200 | 0.1733          | 4.7991 |
| 0.1469        | 1.68  | 1300 | 0.1692          | 4.7227 |
| 0.1157        | 1.81  | 1400 | 0.1688          | 4.7404 |
| 0.1304        | 1.93  | 1500 | 0.1687          | 4.7169 |


### Framework versions

- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0