---
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-E10_Yfreq
  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-E10_Yfreq

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: 0.2085
- Cer: 6.3029

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.2909        | 0.13  | 100  | 0.2830          | 7.4307 |
| 0.1788        | 0.26  | 200  | 0.2478          | 6.5378 |
| 0.1644        | 0.39  | 300  | 0.2375          | 6.4967 |
| 0.1614        | 0.52  | 400  | 0.2265          | 6.3675 |
| 0.1458        | 0.64  | 500  | 0.2243          | 6.1971 |
| 0.1368        | 0.77  | 600  | 0.2217          | 7.0665 |
| 0.1226        | 0.9   | 700  | 0.2216          | 6.3029 |
| 0.0553        | 1.03  | 800  | 0.2162          | 5.9563 |
| 0.0499        | 1.16  | 900  | 0.2187          | 5.9680 |
| 0.0597        | 1.29  | 1000 | 0.2153          | 5.9211 |
| 0.0456        | 1.42  | 1100 | 0.2121          | 6.5789 |
| 0.0495        | 1.55  | 1200 | 0.2128          | 6.6024 |
| 0.0558        | 1.68  | 1300 | 0.2095          | 6.3675 |
| 0.044         | 1.81  | 1400 | 0.2081          | 6.3969 |
| 0.0424        | 1.93  | 1500 | 0.2085          | 6.3029 |


### Framework versions

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