小编Ami*_*nST的帖子

我有此代码适用于英语但不适用于波斯语

from gensim.models import Word2Vec as wv
for sentence in sentences:
    tokens = sentence.strip().lower().split(" ")
    tokenized.append(tokens)
model = wv(tokenized
    ,size=5,
          min_count=1)
print('done2')
model.save('F:/text8/text8-phrases1')
print('done3')
print(model)
model = wv.load('F:/text8/text8-phrases1')

print(model.wv.vocab)

输出

> '??': <gensim.models.keyedvectors.Vocab object at 0x0000027716EEB0B8>,
> '????': <gensim.models.keyedvectors.Vocab object at
> 0x0000027716EEB160>, '??????': <gensim.models.keyedvectors.Vocab
> object at 0x0000027716EEB198>, '???????':
> <gensim.models.keyedvectors.Vocab object at 0x0000027716EEB1D0>,
> '???????': <gensim.models.keyedvectors.Vocab object at
> 0x0000027716EEB208>, '???????': <gensim.models.keyedvectors.Vocab
> object at 0x0000027716EEB240>, '?????':
> <gensim.models.keyedvectors.Vocab object at 0x0000027716EEB278>,
> '?????': <gensim.models.keyedvectors.Vocab object at
> …