Edit model card

Bengali Word2Vec Model

This is a pre-trained word2vec model for Bengali language.

This model is build for bnlp package.

Datasets

Training details

  • Word2Vec word embedding dimension = 100, min_count=5, window=5, epochs=10

Usage

  • pip install -U bnlp_toolkit

  • Generate Vector using pretrain model

    from bnlp import BengaliWord2Vec
    
    bwv = BengaliWord2Vec()
    model_path = "bengali_word2vec.model"
    word = 'গ্রাম'
    vector = bwv.generate_word_vector(model_path, word)
    print(vector.shape)
    print(vector)
    
  • Find Most Similar Word Using Pretrained Model

    from bnlp import BengaliWord2Vec
    
    bwv = BengaliWord2Vec()
    model_path = "bengali_word2vec.model"
    word = 'গ্রাম'
    similar = bwv.most_similar(model_path, word, topn=10)
    print(similar)
    
Downloads last month
0
Hosted inference API

Unable to determine this model’s pipeline type. Check the docs .