---
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-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-E10_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: 0.2060
- Cer: 5.8917

## 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    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.3564        | 0.13  | 100  | 0.2919          | 7.1898 |
| 0.2354        | 0.26  | 200  | 0.2478          | 6.7023 |
| 0.21          | 0.39  | 300  | 0.2349          | 7.3191 |
| 0.1999        | 0.52  | 400  | 0.2270          | 7.0665 |
| 0.1883        | 0.64  | 500  | 0.2227          | 6.8961 |
| 0.1844        | 0.77  | 600  | 0.2195          | 6.4027 |
| 0.1631        | 0.9   | 700  | 0.2156          | 6.1560 |
| 0.0977        | 1.03  | 800  | 0.2142          | 6.0738 |
| 0.087         | 1.16  | 900  | 0.2144          | 6.0385 |
| 0.0985        | 1.29  | 1000 | 0.2119          | 6.0033 |
| 0.0763        | 1.42  | 1100 | 0.2110          | 5.9034 |
| 0.0906        | 1.55  | 1200 | 0.2088          | 5.8741 |
| 0.0922        | 1.68  | 1300 | 0.2066          | 5.8564 |
| 0.079         | 1.81  | 1400 | 0.2060          | 5.8623 |
| 0.0771        | 1.93  | 1500 | 0.2060          | 5.8917 |


### Framework versions

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