GIZ NLP Agricultural Keyword Spotter
$7,000 USD
Classify audio utterances in Luganda and English from Uganda
715 data scientists enrolled, 255 on the leaderboard
AgricultureClassificationAudioNLPUnstructuredSDG2
Uganda
11 September 2020—29 November 2020
80 days
Error Loading dataset
published 18 Nov 2020, 12:35

Please help me, I am new to NLP and Audio datasets. I tried using torchaudio to load my audiofiles into Jupiter Notebook. says file not found.

here is the path where I have saved the unzipped audio files.

filename = "C:/Users/user/........./........../........../GIZ NLP data/audio_files"

waveform, sample_rate = torchaudio.load(filename)

the error message:

OSError Traceback (most recent call last) <ipython-input-17-07a4609d07c9> in <module> 6 7 filename = "C:/Users/user/........./........../........../GIZ NLP data/audio_files" ----> 8 waveform, sample_rate = torchaudio.load(filename) 9 10 print("Shape of waveform: {}".format(waveform.size())) ~\Anaconda3\lib\site-packages\torchaudio\backend\soundfile_backend.py in load(filepath, out, normalization, channels_first, num_frames, offset, signalinfo, encodinginfo, filetype) 48 # check if valid file 49 if not os.path.isfile(filepath): ---> 50 raise OSError("{} not found or is a directory".format(filepath)) 51 52 if num_frames < -1: OSError: C:/Users/user/........./........../........../GIZ NLP data/audio_files not found or is a directory

thanks

C:/Users/user/........./........../........../GIZ NLP data/audio_files. This is a directory. To specify the filename you have to give the name of the file such as:

C:/Users/user/........./........../........../GIZ NLP data/audio_files/ABC.wav if the file name is named as ABC

I tried it....just as you have said...still the same error