# Aligning torchtext vocab index to loaded embedding pre-trained weights

**URL:** <https://discuss.pytorch.org/t/aligning-torchtext-vocab-index-to-loaded-embedding-pre-trained-weights/20878>\
**Category:** nlp\
**Created:** [July 9, 2018, 1:24am UTC](https://discuss.pytorch.org/t/aligning-torchtext-vocab-index-to-loaded-embedding-pre-trained-weights/20878 "2018-07-09T01:24:42Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![Todd\_Morrill](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/todd_morrill/32/23959_2.png) [@Todd\_Morrill](https://discuss.pytorch.org/u/Todd_Morrill)\
**Post date:** [June 27, 2020, 8:38pm UTC](https://discuss.pytorch.org/t/aligning-torchtext-vocab-index-to-loaded-embedding-pre-trained-weights/20878/8 "2020-06-27T20:38:26Z")

</div>

Hi Naresh - I saved two crucial artifacts as part of fasttext training in `gensim` and surely these techniques will apply to word2vec training in `gensim` as well.

First, I saved the word embeddings in the w2v text file format.

```auto
...
    # save w2v format since this is useful for PyTorch
    if save_w2v:
        w2v_out_filepath = os.path.join(save_dir, f'{file_name}_w2vformat.txt')
        model.wv.save_word2vec_format(w2v_out_filepath)
        print(f'Saved {w2v_out_filepath}')
...

```

Second, I saved the word frequency `Counter` dictionary that is required by `torchtext.vocab.Vocab`.

```auto
...
   # save word frequencies since this is useful for PyTorch
    counts = Counter(
        {word: vocab.count
         for (word, vocab) in model.wv.vocab.items()})
    freq_filepath = os.path.join(save_dir, f'{file_name}_word_freq.json')
    save_json(freq_filepath, counts)
    print(f'Saved {freq_filepath}')
...

```

Then I load these files into `torchtext.vocab.Vectors` and `torchtext.vocab.Vocab` objects, respectively, as described above, and it all comes together beautifully.

I hope that helps!

---

_[View the full topic](https://discuss.pytorch.org/t/aligning-torchtext-vocab-index-to-loaded-embedding-pre-trained-weights/20878)._