{"id":41662813,"url":"https://github.com/suriyadeepan/language-modeling","last_synced_at":"2026-01-24T17:12:19.906Z","repository":{"id":86896543,"uuid":"78111416","full_name":"suriyadeepan/language-modeling","owner":"suriyadeepan","description":"Language Modeling with RNN in Tensorflow","archived":false,"fork":false,"pushed_at":"2017-01-06T18:19:39.000Z","size":1108,"stargazers_count":5,"open_issues_count":0,"forks_count":4,"subscribers_count":5,"default_branch":"master","last_synced_at":"2024-01-29T07:35:35.386Z","etag":null,"topics":["language","modeling","rnn","tensorflow"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/suriyadeepan.png","metadata":{"files":{"readme":"README.markdown","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":"2017-01-05T12:33:35.000Z","updated_at":"2019-07-21T11:34:45.000Z","dependencies_parsed_at":"2023-05-29T18:15:41.700Z","dependency_job_id":null,"html_url":"https://github.com/suriyadeepan/language-modeling","commit_stats":{"total_commits":20,"total_committers":1,"mean_commits":20.0,"dds":0.0,"last_synced_commit":"f77305be41b0234562a98a1aedc006de95aefc4c"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/suriyadeepan/language-modeling","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suriyadeepan%2Flanguage-modeling","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suriyadeepan%2Flanguage-modeling/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suriyadeepan%2Flanguage-modeling/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suriyadeepan%2Flanguage-modeling/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/suriyadeepan","download_url":"https://codeload.github.com/suriyadeepan/language-modeling/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/suriyadeepan%2Flanguage-modeling/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28732260,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-24T10:24:43.181Z","status":"ssl_error","status_checked_at":"2026-01-24T10:24:36.112Z","response_time":89,"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":["language","modeling","rnn","tensorflow"],"created_at":"2026-01-24T17:12:19.328Z","updated_at":"2026-01-24T17:12:19.882Z","avatar_url":"https://github.com/suriyadeepan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Language Modeling in Tensorflow\n\nLanguage Modeling with Dynamic Recurrent Neural Networks, in Tensorflow.\n\n\n## How to use custom data?\n\nYou can train the model on any data. Just make sure to put the text in a single file (see [tensorflow.txt](data/tensorflow/tensorflow.txt) for example). Create a configuration file. Specify a data path, checkpoint path, the name of your data file and the hyperparameters of the model.\n\n*Sample configuration file*\n\n```ini\n[str]\ndata_path= data/tensorflow/\nckpt_path= ckpt/tensorflow/ \nmodel_name= tf_lm\ndata_file= data/tensorflow/tensorflow.txt\n[int]\nbatch_size= 128\nnum_layers= 2\nstate_size= 128\n[float]\nlearning_rate= 0.1\n```\n\n*train*\n\n```bash\npython3 train.py tf_src_code.ini\n```\n\n*generate text*\n\n```bash\npython3 generate.py tf_src_code.ini d 1000\n# start with initial character 'd'\n#  generate 1000 characters\n```\n\n\n## Sample Hallunications\n\n\n*SMS messages*\n\nI gathered the spam messages in my phone's inbox, accumulated over the past 2 years (roughly 2000 messages). Used a 2 layered stacked-LSTM RNN to model it. Generates non-sensical [text](https://gist.github.com/suriyadeepan/d8c59e22b177d13d4141051546cde0d7), which resembles the spam messages.\n\n\u003e [WAP Push] Download App starting from Bangalont koud spepout 899 \u0026 17-1GB D\n\u003e Open bit.ly/fontkm.bovk Stapers Prady-100 SMonil Jontal Talk trestroup on !7 6/2 \u0026 bear starting so\n\u003e Bangy offer OFFV send mang rides. Seb110 ya Details OFFER  Anjonations? Talk Meleare tilp 1051\n\u003e FREE Listen \u0026 Select) paytmathi Special ABuree Dial Maghone T\u0026C-Jour phase . Men:tipes!    Entreats, \n\u003e http://wap.D20113. on 1503.BSNL TN VAS\n\u003e //122.176.201620Bug,220dy today 20MB DHAYS .Use VEERIWN\n\n*Project Madurai*\n\nElectronic versions of printed texts of [ancient tamil literary works](http://www.projectmadurai.org/) - pedagoic and scholarly resources. Scraped 4.1 GB worth of text from Project Madurai. The script for scraping is available [here](data/madurai/scrape.py). Hallucinations are available [here](https://gist.github.com/suriyadeepan/ee852656cde5720232879f5bf43945b9).\n\n\u003e பிரியுங் கயுமெலாம் அறுத்தான்\n\u003e மூத்தரசூதைமுலைமகம்குக் கப்புல்லத்திட்டுப்\n\u003e பாரின்ப வந்துபொறும் மாடேன் பரங்கரு ணையளிக்குந் தோர்புருட கலசைப் பைந்தி.\n\u003e ஓலக்கினேன்குழலே சேரும்வண்ணம் இறுமுற்றுமக்கீளலொட்டி\n\u003e ஓராமனம் என்றருளாய் பிறேன் சாலகத்துஅங்காண்பான் அம்மான் தளரின்மனவுமெய்தாற்\n\u003e பூந்துவரை அவங்கு இவையா\n\u003e ளாவாரணல்கள்வார் பிரிவரிய அன்பரந்த\n\u003e வொத்தன் பெருந்துறையான்\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsuriyadeepan%2Flanguage-modeling","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsuriyadeepan%2Flanguage-modeling","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsuriyadeepan%2Flanguage-modeling/lists"}