{"id":17317467,"url":"https://github.com/cdpierse/script_buddy_v2","last_synced_at":"2025-08-22T20:10:40.447Z","repository":{"id":37060978,"uuid":"228940256","full_name":"cdpierse/script_buddy_v2","owner":"cdpierse","description":"Script Buddy v2 is a film script text generation tool built using film scripts from the world's most popular film scripts and GPT2.","archived":false,"fork":false,"pushed_at":"2023-07-23T00:46:03.000Z","size":87849,"stargazers_count":47,"open_issues_count":8,"forks_count":22,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-06-04T05:12:38.843Z","etag":null,"topics":["artificial-intelligence","gpt-2","language-generation","machine-learning","nlp","pytorch","transformers"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/cdpierse.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,"governance":null}},"created_at":"2019-12-18T23:48:54.000Z","updated_at":"2023-10-20T19:41:48.000Z","dependencies_parsed_at":"2023-01-20T14:32:49.860Z","dependency_job_id":"b544e403-e5d1-4660-82ad-20b9a66d651e","html_url":"https://github.com/cdpierse/script_buddy_v2","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/cdpierse/script_buddy_v2","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cdpierse%2Fscript_buddy_v2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cdpierse%2Fscript_buddy_v2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cdpierse%2Fscript_buddy_v2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cdpierse%2Fscript_buddy_v2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cdpierse","download_url":"https://codeload.github.com/cdpierse/script_buddy_v2/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cdpierse%2Fscript_buddy_v2/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261984649,"owners_count":23240303,"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":["artificial-intelligence","gpt-2","language-generation","machine-learning","nlp","pytorch","transformers"],"created_at":"2024-10-15T13:16:46.128Z","updated_at":"2025-06-26T02:04:46.989Z","avatar_url":"https://github.com/cdpierse.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# script_buddy_v2\n Script Buddy v2 is a film script text generation tool built using film scripts from the world's most popular film scripts. \n\n Read more about the project on [Medium](https://towardsdatascience.com/film-script-generation-with-gpt-2-58601b00d371?source=friends_link\u0026sk=934ac3ac7079d34bae215ce9a558986a) \n\n I'm also a bot on twitter, I tweet a new script snippet every hour or so, follow me at [@script_buddy](https://twitter.com/script_buddy)\n\n\n\n![Script Buddy APP](script_buddy/images/app.gif)\n \n## Project Structure \n- *imsdb_scraper* contains the scrapy spider built to crawl IMSDB.com and download the film script data that is used to train our text generation model. \n\n    - To run the scraper change directory to imsdb_scraper with `cd imsdb_scraper`. As I haven't built any pipelines currently to run the scraper and save it's output simply run `scrapy crawl scriptSpider  -o scripts.json -t json` and for now manually move this output file to `script_buddy/data/` and you'll be good to go. \n\n- *script_buddy* contains the model fine tuning notebook, utility script parsing functions, tweepy bot code, and streamlit application code. \n    - If you'd like to run the streamlit app locally \n        - `git clone https://github.com/cdpierse/script_buddy_v2.git` \n        - `pip install -r requirements.txt`\n        - `cd script_buddy`\n        - `streamlit run app.py`\n\n    - This should open an instance of the app for you to experiment with. Running it for the first time may take a \n    while as the model needs to be downloaded from huggingface's model hub. \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcdpierse%2Fscript_buddy_v2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcdpierse%2Fscript_buddy_v2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcdpierse%2Fscript_buddy_v2/lists"}