---
title: exp-audio-recorder
app_file: web.py
sdk: gradio
sdk_version: 5.31.0
---
# Audio Understanding

[Super AI Engineer 2025 (Level 2) - Signal Processing & Natural Language Processing Hackathon](https://www.kaggle.com/competitions/audio-understanding/)

## Getting Started

Clone and set up the project:
```
git clone https://gitlab.local.aiat.or.th/superaiss5/exp/audio-understanding.git
```

Link with existing repository:
```
cd existing_repo
git remote add origin https://gitlab.local.aiat.or.th/superaiss5/exp/audio-understanding.git
git branch -M main
git push -uf origin main
```

## Project Structure


## Dataset

- train.csv - the training set
- speechs/ - This folder contains the training set with 100 wav files & 300 test set with 300 wav files
- test.csv - a submission file in the correct format contains with a story

## Rules

External datasets are allowed.
Only local models may be used.
This dataset will be used exclusively for this competition.
APIs for data augmentation are allowed.

## Evaluation

Evaluation Metric: F2-score (ß=2)

## Test and Deploy


## Authors and acknowledgment
Show your appreciation to those who have contributed to the project.

## License