{"id":15553585,"url":"https://github.com/sagorbrur/itranslit","last_synced_at":"2025-04-10T19:33:06.124Z","repository":{"id":62571943,"uuid":"362798859","full_name":"sagorbrur/itranslit","owner":"sagorbrur","description":"transliteration for indic language","archived":false,"fork":false,"pushed_at":"2021-05-29T18:51:55.000Z","size":38,"stargazers_count":4,"open_issues_count":1,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-24T17:11:28.800Z","etag":null,"topics":["bengali-transliteration","deep-learning","gujarati-transliteration","hindi-transliteration","indic-languages","indic-transliteration","malayalam-transliteration","nlp","punjabi-transliteration","pytorch","tamil-transliteration","transliteration","urdu-transliteration"],"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/sagorbrur.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":"2021-04-29T11:48:13.000Z","updated_at":"2025-03-18T14:10:51.000Z","dependencies_parsed_at":"2022-11-04T00:38:42.129Z","dependency_job_id":null,"html_url":"https://github.com/sagorbrur/itranslit","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sagorbrur%2Fitranslit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sagorbrur%2Fitranslit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sagorbrur%2Fitranslit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sagorbrur%2Fitranslit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sagorbrur","download_url":"https://codeload.github.com/sagorbrur/itranslit/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248281416,"owners_count":21077423,"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":["bengali-transliteration","deep-learning","gujarati-transliteration","hindi-transliteration","indic-languages","indic-transliteration","malayalam-transliteration","nlp","punjabi-transliteration","pytorch","tamil-transliteration","transliteration","urdu-transliteration"],"created_at":"2024-10-02T14:39:25.461Z","updated_at":"2025-04-10T19:33:06.097Z","avatar_url":"https://github.com/sagorbrur.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# iTRANSLIT\n__iTRANSLIT__ is a deep learning based transliteration package for indic language\n\n## Installation\n```pip install itranslit```\n\n## Dependency\n- `pytorch 1.7.0 or 1.7.0+`\n\nNB: No `GPU` need. It's `CPU` based.\n\n## Supported Language and Language Code\n| __Language Name__ | __Langauage Code__ |\n| --- | :-- |\n| Bangla | bn |\n| Gujarati| gu |\n| Hindi | hi |\n| Punjabi | pa |\n| Sindhi | sd |\n| Urdu | ur |\n| Malayalam | ml |\n| Tamil | ta |\n|    |      |\n\n\n## API\n\n```py\nfrom itranslit import Translit\n\ntranslit = Translit('bn')\nword = \"aami\"\noutput = translit.predict(word, topk=10)\nprint(output)\n\n```\n\n## Datasets and Training Details\n- We used [Google Dakshina Dataset](https://github.com/google-research-datasets/dakshina)\n- Thanks to [AI4Bharat](https://github.com/AI4Bharat/IndianNLP-Transliteration) for providing training notebook with details explanation\n- We trained Google Dakshina lexicons train datasets for 10 epochs with batch size 128, 1e-3, embedding dim = 300, hidden dim = 512, lstm, used attention\n- We evaluated our trained model with Google Dakshina lexicon test data using [AI4Bharat evaluation script](https://raw.githubusercontent.com/AI4Bharat/IndianNLP-Transliteration/jgeob-dev/tools/accuracy_reporter/accuracy_news.py)\n- You can find evaluation summary [here](docs/evaluations)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsagorbrur%2Fitranslit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsagorbrur%2Fitranslit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsagorbrur%2Fitranslit/lists"}