{"id":15293045,"url":"https://github.com/akb89/word2vec","last_synced_at":"2026-03-14T02:05:46.386Z","repository":{"id":34647657,"uuid":"179023880","full_name":"akb89/word2vec","owner":"akb89","description":"Re-implementation of Word2Vec using Tensorflow v2 Estimators and Datasets","archived":false,"fork":false,"pushed_at":"2023-03-25T01:19:46.000Z","size":5455,"stargazers_count":11,"open_issues_count":2,"forks_count":5,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-05T17:57:38.003Z","etag":null,"topics":["tensorflow","tensorflow-datasets","tensorflow-estimators","tensorflow2","word2vec"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/akb89.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2019-04-02T07:35:22.000Z","updated_at":"2024-09-13T13:33:57.000Z","dependencies_parsed_at":"2023-01-15T08:20:08.543Z","dependency_job_id":null,"html_url":"https://github.com/akb89/word2vec","commit_stats":null,"previous_names":[],"tags_count":11,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akb89%2Fword2vec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akb89%2Fword2vec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akb89%2Fword2vec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/akb89%2Fword2vec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/akb89","download_url":"https://codeload.github.com/akb89/word2vec/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239379345,"owners_count":19628685,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["tensorflow","tensorflow-datasets","tensorflow-estimators","tensorflow2","word2vec"],"created_at":"2024-09-30T16:38:44.776Z","updated_at":"2026-03-14T02:05:41.362Z","avatar_url":"https://github.com/akb89.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Word2Vec\n\n[![GitHub release][release-image]][release-url]\n[![PyPI release][pypi-image]][pypi-url]\n[![Build][travis-image]][travis-url]\n[![MIT License][license-image]][license-url]\n\nThis is a re-implementation of Word2Vec relying on Tensorflow\n[Estimators](https://www.tensorflow.org/guide/estimators) and\n[Datasets](https://www.tensorflow.org/guide/datasets_for_estimators).\n\nWorks with python \u003e= 3.6 and Tensorflow v2.0.\n\n## Install\nvia pip:\n```shell\npip3 install tf-word2vec\n```\nor, after a git clone:\n```shell\npython3 setup.py install\n```\n\n## Get data\nYou can download a sample of the English Wikipedia here:\n```shell\nwget http://129.194.21.122/~kabbach/enwiki.20190120.sample10.0.balanced.txt.7z\n```\n\n## Train Word2Vec\n```shell\nw2v train \\\n  --data /absolute/path/to/enwiki.20190120.sample10.0.balanced.txt \\\n  --outputdir /absolute/path/to/word2vec/models \\\n  --alpha 0.025 \\\n  --neg 5 \\\n  --window 2 \\\n  --epochs 5 \\\n  --size 300 \\\n  --min-count 50 \\\n  --sample 1e-5 \\\n  --train-mode skipgram \\\n  --t-num-threads 20 \\\n  --p-num-threads 25 \\\n  --keep-checkpoint-max 3 \\\n  --batch 1 \\\n  --shuffling-buffer-size 10000 \\\n  --save-summary-steps 10000 \\\n  --save-checkpoints-steps 100000 \\\n  --log-step-count-steps 10000\n```\n\n[release-image]:https://img.shields.io/github/release/akb89/word2vec.svg?style=flat-square\n[release-url]:https://github.com/akb89/word2vec/releases/latest\n[pypi-image]:https://img.shields.io/pypi/v/tf-word2vec.svg?style=flat-square\n[pypi-url]:https://pypi.org/project/tf-word2vec/\n[travis-image]:https://img.shields.io/travis/akb89/word2vec.svg?style=flat-square\n[travis-url]:https://travis-ci.org/akb89/word2vec\n[license-image]:http://img.shields.io/badge/license-MIT-000000.svg?style=flat-square\n[license-url]:LICENSE.txt\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakb89%2Fword2vec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fakb89%2Fword2vec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fakb89%2Fword2vec/lists"}