{"id":18437499,"url":"https://github.com/stoufa/neural-machine-translation_transliteration","last_synced_at":"2026-04-25T21:34:28.129Z","repository":{"id":184783802,"uuid":"130661299","full_name":"stoufa/Neural-Machine-Translation_Transliteration","owner":"stoufa","description":"An Intelligent Approach for Translation / Transliteration using Neural Networks","archived":false,"fork":false,"pushed_at":"2018-12-24T13:17:00.000Z","size":300,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-14T14:59:03.977Z","etag":null,"topics":["attention-mechanism","character-embeddings","fasttext","neural-machine-translation","nlp","pytorch","rnn-encoder-decoder","translation","transliteration","word-embeddings"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/stoufa.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2018-04-23T08:01:33.000Z","updated_at":"2018-12-24T13:17:02.000Z","dependencies_parsed_at":"2023-07-30T08:29:30.367Z","dependency_job_id":"e9d353c2-b2bc-49ac-9a8e-6dc13f8c24db","html_url":"https://github.com/stoufa/Neural-Machine-Translation_Transliteration","commit_stats":null,"previous_names":["stoufa/neural-machine-translation_transliteration"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/stoufa/Neural-Machine-Translation_Transliteration","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stoufa%2FNeural-Machine-Translation_Transliteration","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stoufa%2FNeural-Machine-Translation_Transliteration/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stoufa%2FNeural-Machine-Translation_Transliteration/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stoufa%2FNeural-Machine-Translation_Transliteration/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/stoufa","download_url":"https://codeload.github.com/stoufa/Neural-Machine-Translation_Transliteration/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/stoufa%2FNeural-Machine-Translation_Transliteration/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32278249,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-25T18:29:39.964Z","status":"ssl_error","status_checked_at":"2026-04-25T18:29:32.149Z","response_time":59,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["attention-mechanism","character-embeddings","fasttext","neural-machine-translation","nlp","pytorch","rnn-encoder-decoder","translation","transliteration","word-embeddings"],"created_at":"2024-11-06T06:15:00.574Z","updated_at":"2026-04-25T21:34:28.115Z","avatar_url":"https://github.com/stoufa.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural-Machine-Translation_Transliteration\nAn Intelligent Approach for Translation / Transliteration using Neural Networks\n\nThis translation approach is based on Recurrent Neural Networks (RNNs) which are the type of Neural Networks to be used when dealing with sequences of input like videos, sound or text like in our case.\n\n![RNNs](https://camo.githubusercontent.com/c847d37b28afbb2cf3c73bb428354308e16f5efc/68747470733a2f2f63646e2d696d616765732d312e6d656469756d2e636f6d2f6d61782f3830302f312a445537373653477231726859655537696c494b5839772e706e67)\n\nFor the data, I used the [bible-corpus](http://christos-c.com/bible/), you have to download the corresponding raw XML files and place them in the directory (`data/bible-corpus/raw/`) then extract the text from these files : you can use the Jupyter Notebook (`word-character embedding/XMLparser.ipynb`) to help you in this task, then save the results in the directory (`data/bible-corpus/pre-processed/`) and finaly run the script (`createEmbeddings.sh`) to generate the embeddings in the directory (`data/bible-corpus/processed/`).\n\nBy the way, I used [Fasttext](https://fasttext.cc/) for the embeddings.\n\nThe script (`word-character embedding/getEmbedding.py`) reads a word or a character from the user and checks if the embedding is already saved in the SQLite database (`word-character embedding/embeddingDB.db`), otherwise, it computes it using Fasttext even if it's not found in the training corpus! in this case, it will generate the closest embedding based on the word's characters.\n\nThe Jupyter Notebook `translate_dev.ipynb` explains the whole pipeline which starts by reading in the training data, tokenization, embedding then building and training the model.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstoufa%2Fneural-machine-translation_transliteration","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstoufa%2Fneural-machine-translation_transliteration","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstoufa%2Fneural-machine-translation_transliteration/lists"}