GIZ NLP Agricultural Keyword Spotter
$7,000 USD
Classify audio utterances in Luganda and English from Uganda
673 data scientists enrolled, 231 on the leaderboard
11 September—29 November 23:59
Ends in 65 hours
Failed submission
published 10 Nov 2020, 12:11

Hi everyone,

I've just tried submitting my first solution, but after uploading my csv file, I get the following comment:

"Missing entries for IDs audio_files/00P0NMV.wav, audio_files/066NU27.wav, audio_files/0K9OULT.wav, audio_files/0MV7LQS.wav, audio_files/0OTDVG8.wav and more"

I've checked my csv file to see if those entries are really missing, and they don't. Has anyone had the same problem as me?


Are there any empty cells in you submission CSV in the lines corresponding to these IDs?

I think you also need to make Sure that they appear in the same order as in the sample Submission

Thanks for your reply. I checked again and the order is the same, and there are no empty cells... as far as can I see, my csv has the exact same structure as SampleSubmission.csv

Be sure that the paths in your submission file is like: 'audio_files/mywav.wav'

Thanks, this really helped since I was working using Google Colabo and just slipped my mind when I tried to make my submission

Ha, I've figured it out. When downloading the csv file, I have to set index_False, like so:

df.to_csv('submission.csv', index=False)

So the fault wasn't with the file names but with the indexing.