# ENSIM Language Identification (LID) 2025 — Data

来源：https://www.kaggle.com/competitions/ensim-language-identification-lid-2025/data

采集时间：2026-10-19T12:41:25Z

The provided dataset has been collected from [TEDx talks YouTube](https://www.youtube.com/user/TEDxTalks) for the Language Identification task from audio.
The samples are recorded audio of speaker speech from available TEDx talks videos.  
In order to have a standard sample's type, they follow below convention.

- The length of recorded audio files should be around 5 seconds (5.00 - 5.99 seconds).
- The format of audio files should be *.wav.
- The sample rate of recording files should be 16 kHz (in mono format).


## Dataset

A repository contains recording files in the standard format (*.wav, 16kHz, mono, 5-6 seconds) and a *.txt file with 4 information (separated by , ) for each recorded file (one file per line) has been provided.

- The 1st column is the name of *.wav file
- The 2nd column is the URL address of YouTube video
- The 3rd column is the starting time of recording from YouTube video
- The 4th column is the label (language) of recorded speech (EN, FR, AR, JP)

## Evaluation set

A repository contains recording files in the standard format (*.wav, 16kHz, mono, 5-6 seconds) and a *.txt file with 2 columns as the file names and a the predicted label by your classification model.