OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Script Buddy V2

Script Buddy V2 is an open-source film-script text-generation project built around GPT-2 fine-tuned on film scripts. Its repository includes a Streamlit app, a fine-tuning notebook, script-parsing utilities, a Scrapy-based script-data scraper and Twitter bot code.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Script Buddy V2 — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a repository-based example of film-script text generation and are prepared to run the Streamlit app locally or inspect its data and model components.

Who it is for

  • People who want to experiment with GPT-2-based film-script text generation through a Streamlit app.
  • Developers exploring a small text-generation project with script parsing, data collection and model fine-tuning components.

Documented uses

  • Generate film-script-style text in the Streamlit app.
  • Collect film-script data into a JSON file using the included Scrapy spider.
  • Explore the project's notebook and utilities for fine-tuning and parsing script text.
Before you choose

Requirements & limits

The project is published under the MIT license. The README documents local app setup; it does not describe a hosted app.

  • The first local app run may take longer because it downloads the model from Hugging Face's model hub.
  • The scraper exports JSON, but placing the output in the app's data directory is a manual step.
  • The repository also contains Twitter bot code that publishes script snippets; the README describes posting about once per hour.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Streamlit app locally

Install the repository requirements and launch the documented app entry point.

Before you start

  • A local environment capable of cloning the public GitHub repository and installing its requirements.
  • Internet access for the first-run download of the model from Hugging Face's model hub.

Steps

  1. Clone https://github.com/cdpierse/script_buddy_v2.git.

  2. Run the command below from the cloned repository.

    Documented command
    pip install -r requirements.txt

  3. Change into the script_buddy directory.

  4. Run streamlit run app.py.

Expected outcome

The README says this opens an instance of the app for experimenting with film-script text generation.

Guide limitations

  • The first run may take a while while the model downloads.
Documentation 1 ↗
Source-based practical guide

Collect script data with the Scrapy spider

Export the spider's collected film-script data to JSON and place the file in the app's data directory.

Before you start

  • The repository's imsdb_scraper component and a Scrapy environment.

Steps

  1. Change into the imsdb_scraper directory.

  2. Run scrapy crawl scriptSpider -o scripts.json -t json.

  3. Manually move the resulting scripts.json file to script_buddy/data/.

Expected outcome

The scraped output is placed in the data directory identified by the README for the model project.

Guide limitations

  • The README says there is no pipeline to save the scraper output automatically.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
cdpierse/script_buddy_v2 · Official homepage title · retained in its source language
How we review sourcesSuggest a correction