aitoralmeida / spanish_word2vec Goto Github PK

Hello,

Is there any chance of having this corpus trained with fasttext?

That would help me a lot.

Is a much smaller file so if the only thing you want are the vectors itself its more easy to download than the NN Model.

IC: https://radimrehurek.com/gensim/models/keyedvectors.html#gensim.models.keyedvectors.KeyedVectors

I'm getting errors when trying to load the model. Do you have any suggestions?

model = Word2Vec.load('./models/complete.model')

Traceback (most recent call last):
File "", line 1, in
File "/home/user/.local/lib/python3.8/site-packages/gensim/models/word2vec.py", line 1934, in load
raise ae
File "/home/user/.local/lib/python3.8/site-packages/gensim/models/word2vec.py", line 1922, in load
model = super(Word2Vec, cls).load(*args, **kwargs)
File "/home/user/.local/lib/python3.8/site-packages/gensim/utils.py", line 486, in load
obj = unpickle(fname)
File "/home/user/.local/lib/python3.8/site-packages/gensim/utils.py", line 1458, in unpickle
return _pickle.load(f, encoding='latin1') # needed because loading from S3 doesn't support readline()
AttributeError: Can't get attribute 'Vocab' on <module 'gensim.models.word2vec' from '/home/user/.local/lib/python3.8/site-packages/gensim/models/word2vec.py'>

Update: The model appears not to fail loading when using gensim=3.8.1. However, python crashes when loading. I assume memory issues (?)

Hello,

I'm wondering where can I download the Spanish corpora used here?

Many thanks!

Hello, is this Word2vec pre-trained model CBOW or Skip-Gram?