Error while loading the bin file

[gitlost-murali]

I have downloaded the pre trained hindi word2vec model.I loaded the binary file using "model = gensim.models.KeyedVectors.load_word2vec_format('hi.bin',binary=True)"

But I get the following error: " File "C:\Users***\AppData\Local\Programs\Python\Python35\lib\site-packages\gensim\utils.py", line 240, in any2unicode return unicode(text, encoding, errors=errors) UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 0: invalid start byte"

I have tried this on python3.5,python 2.7 but couldn't escape from the error.

[gitlost-murali]

model = gensim.models.KeyedVectors.load( 'hi.bin')

this solved my problem but can't go further,I am unable to figure out a way to get vector from the word. I tried using model.wv['wordinLanguage'] KeyError: "word '?????????' not in vocabulary" how to deal with this.?

[BrazilForever11]

@Murali81 How did you figure it out? It would be awesome, if author would post some tutorial on how to read embeddings. By the way, polyglot seems to be not working. So this project has great value!

[ksopyla]

If you want to load one of the language word2vec file with gensim 3.0 and python3.5 you can use this snippet

    from gensim.models.keyedvectors import KeyedVectors
    embeddings_file_bin = 'data/pl.bin'
    model_bin = KeyedVectors.load(embeddings_file_bin)
    print(model_bin['kot'])

[gitlost-murali]

Thanks

[kusumlata123]

embeddings_file_bin = 'data/pl.bin here what is 'data/pl.bin

[gayatrivenugopal]

Tried using load() but getting an error: AttributeError: 'Word2Vec' object has no attribute 'vocabulary'

[caitaozhan]

Tried using load() but getting an error: AttributeError: 'Word2Vec' object has no attribute 'vocabulary'

I had similar issues and solved it by degrading my gensim version from 3.6 to 3.0