---
language:
- ko
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-large-v2
datasets:
- mozilla-foundation/common_voice_17_0
model-index:
- name: Fast Whisper Small Ko - Youngsu Jo
  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. -->

# Fast Whisper Small Ko - Youngsu Jo

This model is a fine-tuned version of [openai/fast_whisper-Large_v2](https://huggingface.co/openai/fast_whisper-Large_v2) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2606

## 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: 0.001
- train_batch_size: 8
- 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: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.6398        | 1.1236 | 100  | 0.2606          |


### Framework versions

- PEFT 0.10.1.dev0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1