# 1871 AI Tech Challenge 2023 — Data

来源：https://www.kaggle.com/competitions/1871-ai-tech-challenge-2023/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

# About Dataset

## General Information

The data for this challenge has been sourced from a Kaggle public dataset (https://www.kaggle.com/datasets/mozillaorg/common-voice?resource=download). Common Voice is a corpus of speech data read by users on the Common Voice website (http://voice.mozilla.org/), and based upon text from a number of public domain sources like user submitted blog posts, old books, movies, and other public speech corpora. Its primary purpose is to enable the training and testing of automatic speech recognition (ASR) systems.

## Structure

There is an audio zip folder that holds all of the audio clips. The path to these files is included as a value in the train data that accompanies the audio.

Each row of a csv file represents a single audio clip, and contains the following information:
id - unique identifier for that clip
filename - relative path of the audio file within the audio zip folder
text - supposed transcription of the audio
up_votes - number of people who said audio matches the text
down_votes - number of people who said audio does not match text

These final two columns indicate how accurate the training transcription text is. Because some callers may have loud background noise or may be otherwise hard to understand, we have included data that has uncertain transcriptions. This may be used to guide how you train on the data.

## Files

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format