Chakin: search and download pre-trained word vectors

Understand the project

Practical overview

Use Chakin when a project needs a supported pre-trained word-vector file and you want to search listed options before downloading it.

Python developers preparing word embeddings for natural-language-processing projects
Researchers comparing supported vectors by language, dimension or corpus before downloading

Before you choose

The catalog spans multiple languages, but the listed GloVe and word2vec examples are English-focused.
Available options differ in dimension and corpus; the README exposes these details in search results and its supported-vectors table.
Chakin's documented role ends at downloading vectors; downstream loading and use happen in a separate workflow.
The repository identifies the project as MIT-licensed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the package, search its English vector catalog and download the fastText English file to the current directory.

Install the package with the command below.
Documented command
```
pip install chakin
```
In Python, import chakin and call chakin.search(lang='English') to view the listed English vectors.
Call chakin.download(number=2, save_dir='./') to select the fastText English entry shown in the README example.

The documented example returns `./wiki.en.vec` as the saved file path.

The example's selection uses a catalog number; confirm the displayed listing before choosing an entry.
The guide covers retrieval only, not loading or using the vector file in a downstream model.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 17 October 2026
Original website title: chakki-works/chakin · Official homepage title · retained in its source language