The total file size of the Food-5K dataset is about 1.16 GB. Here are steps to download food 11 dataset.

https://mmspg.epfl.ch/downloads/food-image-datasets/

Use these commands at linux prompt:

ftp
open tremplin.epfl.ch
FoodImage@grebvm2.epfl.ch
Cahc1moo
get Food-11.zip

Here is the list of some of the modules used for audio-visual processing using deep learning.

chroma: Feature Learning for Chord Recognition: The Deep Chroma Extractor
MFCC: Mel-frequency cepstral coefficients (MFCCs) are coefficients that collectively make up an MFC
TCD-TIMIT: An Audio-Visual Corpus of Continuous Speech
librosa
RBF: Radial Basis Function
HMM: Hidden Markov Model
VGG: Resnet 50
voxceleb-luigi: Luigi pipeline to download VoxCeleb audio from YouTube and extract speaker segments
deepfakes
obamanet
yolo

1) Download the polyglot pickled marathi model
wget http://bit.ly/12FI1xV
mv 12FI1xV polyglot-mt.pkl

2) Extract all the words from the embedding

from polyglot.mapping import Embedding
embeddings=Embedding.load("polyglot-mt.pkl")
with open('myfile.txt', 'w') as fx:
for i in embeddings.vocabulary:
fx.write(i.encode('utf-8')+'\n')

3) Download the wordlist:
https://s3.amazonaws.com/gamabhana/wiki_wordlist.txt