{"id":28720224,"url":"https://github.com/tetsumichiumada/tv_script_generation","last_synced_at":"2026-05-08T06:39:58.273Z","repository":{"id":299062861,"uuid":"164735603","full_name":"TetsumichiUmada/tv_script_generation","owner":"TetsumichiUmada","description":"generate Simpsons TV scripts using RNNs.","archived":false,"fork":false,"pushed_at":"2019-01-08T21:45:04.000Z","size":327,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-06-14T12:43:27.566Z","etag":null,"topics":["long-short-term-memory","python","recurrent-neural-networks","tensorflow"],"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/TetsumichiUmada.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2019-01-08T21:26:41.000Z","updated_at":"2019-01-12T22:32:38.000Z","dependencies_parsed_at":"2025-06-14T12:43:28.764Z","dependency_job_id":"e40e02ad-6761-4753-9a99-c8157a6b4ace","html_url":"https://github.com/TetsumichiUmada/tv_script_generation","commit_stats":null,"previous_names":["tetsumichiumada/tv_script_generation"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/TetsumichiUmada/tv_script_generation","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TetsumichiUmada%2Ftv_script_generation","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TetsumichiUmada%2Ftv_script_generation/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TetsumichiUmada%2Ftv_script_generation/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TetsumichiUmada%2Ftv_script_generation/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TetsumichiUmada","download_url":"https://codeload.github.com/TetsumichiUmada/tv_script_generation/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TetsumichiUmada%2Ftv_script_generation/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269542819,"owners_count":24435174,"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","status":"online","status_checked_at":"2025-08-09T02:00:10.424Z","response_time":111,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["long-short-term-memory","python","recurrent-neural-networks","tensorflow"],"created_at":"2025-06-15T06:30:25.668Z","updated_at":"2025-10-25T11:43:05.688Z","avatar_url":"https://github.com/TetsumichiUmada.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TV Script Generation\n\nIn this project, we generate our own [Simpsons](https://en.wikipedia.org/wiki/The_Simpsons) TV scripts using RNNs. We are using part of the [Simpsons dataset](https://www.kaggle.com/wcukierski/the-simpsons-by-the-data) of scripts from 27 seasons. The Neural Network we build will generate a new TV script for a scene at [Moe's Tavern](https://simpsonswiki.com/wiki/Moe's_Tavern).\n\n## Dataset \nThe original data set is downloaded from the [Simpsons dataset](https://www.kaggle.com/wcukierski/the-simpsons-by-the-data) of scripts from 27 seasons. It contains:\n\n```\nRoughly the number of unique words: 11492\nNumber of scenes: 262\nAverage number of sentences in each scene: 15.248091603053435\nNumber of lines: 4257\nAverage number of words in each line: 11.50434578341555\n```\n\n## Generated script \n\nHere is an example that the RNN model generated after training 60 epochs (it achieved training loss 0.165). The prime word is `moe_szyslak`\n\n```\nmoe_szyslak: ah, she got homesick for her old life, diving for tourist pennies in a micronesian swamp.\nhomer_simpson: oh, cold shoulder, right! andalay!\nmoe_szyslak:(too big) hanh?!!!\nall:(ad lib) oh, sweet mother fat tony.\n\n\nmoe_szyslak:(sighs) i think\nbarney_gumble: uh-oh. my wife was the last of the family-owned teams.\nlenny_leonard: i tried to return my season ticket, but they wouldn't an day, ever will the pigs.\nwayne: i'm really more like me, and get to dinner.\nwalther_hotenhoffer: nein... nein... nein... nein... nein... we got the cash. my clientele-- let it ring; /mr. plow is a ticket. my wife is, moe. i don't know nothin' about how i do anything.\nmoe_szyslak: i had to get edna out of springfield, and that's it?\nmoe_szyslak: no, i tells ya, homer.\nhomer_simpson:(looking at watch)\n```\n\n## Getting Started \n\n1. Clone the repository and navigate to the downloaded folder.\n```\t\nhttps://github.com/TetsumichiUmada/tv_script_generation.git\ncd tv_script_generation\n```\n\n2. Install required packages. \n\n```\npip install -r requirements.txt\n```\n\n3. Open the notebook.\n```\njupyter notebook tv_script_generation.ipynb\n```\n\n## Acknowledgments\n* [Udacity Deep Learning Nanodegree Program](https://www.udacity.com/course/deep-learning-nanodegree--nd101)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftetsumichiumada%2Ftv_script_generation","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftetsumichiumada%2Ftv_script_generation","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftetsumichiumada%2Ftv_script_generation/lists"}