Automated Script Transcription of TVNZ News

TVNZ One News Transcription Project
Overview
I need help transcribing the TVNZ One News episodes from the last 12 months into text files, broken down by individual stories. The goal is to use technology rather than manual transcription to efficiently create clear, accurate records of each episode.

Scope of work
- Transcribe TVNZ One News episodes into separate text files by stories for 12 months that can be put into a folder. https://www.tvnz.co.nz/shows/one-news-at-6pm
- Use technology, such as scraping closed-caption files, to automate transcription.
- Clean and segment text files by removing presenter names, timestamps, symbols, and sponsor mentions.

Additional information
I'm emphasizing the use of technology for efficient transcription. Recommended tools include Playwright, Puppeteer, or yt-dlp to scrape and convert .vtt files to .txt.

Ideal Candidate
- Experience with data scraping tools like Playwright or Puppeteer.
- Proficiency with yt-dlp for handling video and caption files.
- Ability to automate transcription processes using technology.