# DL Sprint - BUET CSE Fest 2022 — Data

来源：https://www.kaggle.com/competitions/dlsprint/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The Dataset paper is available at: [https://arxiv.org/abs/2206.14053](https://arxiv.org/abs/2206.14053). 


The dataset for this competition comprises about 400 hours of Bengali audio clips collected through Common Voice. Your task is to generate the Bengali transcripts for the audios. 

While the training data includes some metadata about the speakers, such metadata will not be provided for any test data. The full dataset (including the Phase 1 Part 1 test set) is publicly available on the Common Voice website. **The participants are prohibited from using the test dataset for training and any such attempt will lead to disqualification.**
 
## Files

*   **train.csv** - the training set
*   **validation.csv** - the validation set
*   **sample_submission.csv** - a sample submission file in the correct format
* **train_files/** - the training audio files
* **validation_files/** - the validation audio files
* **test_files/** - the test audio files. You need to predict the sentence from these audio files.


## Columns

*   `client_id` - unique identifier for each speaker
*   `path` - name of the audio file in corresponding folder
*   `sentence` - the transcript of the audio file
*   `up_votes` - reviewer up votes
*   `down_votes` - reviewer down votes
*   `age` - age of the speaker
*   `gender` - gender of the speaker
*   `accents` - accents of the speaker
*   `locale` - locality of the speaker