textで保存されたgensimの単語分散表現をbinで保存する．

save_word_embedding_text_to_binary.py

import sys
import linecache

from gensim.models import KeyedVectors


def save_word_embedding_text_to_binary(input, output):
    if linecache.getline(input, 1).split() == 2:
        no_header = False
    else:
        no_header = True
    embedding = KeyedVectors.load_word2vec_format(args[1], binary=False, no_header=no_header)
    embedding.save_word2vec_format(args[2], binary=True)


def main(args):
    input = args[1]
    output = args[2]
    save_word_embedding_text_to_binary(input, output)


if __name__ == "__main__":
    args = sys.argv
    main(args)