From Laptop to Cloud: Scaling YouTube Video Transcription with LLMs

My experiments around Summarizing YouTube Videos with LLMs have been working well on my Mac laptop, but I’d really like to run it as a service on a regular schedule. Running the OpenAI Whisper transcription process locally requires more than 1GB that my favorite Digital Ocean droplets provide. Instead I’ve added an option to run it directly against the OpenAI Transcriptions AI (the official OpenAI Python library makes it very easy). To use the online API you’ll need an API key set up either as pay-as-you-go or with a ChatGPT Plus subscription (which is what I have). After I’ve run…

Continue Reading →

Summarizing YouTube Videos with LLMs

Over the holiday break I was thinking about taking transcriptions of YouTube videos and running them through an LLM for summaries. My inspiration was the dust up around Honey coupon code browser extension. Most of the news pointed to MegaLag’s video Exposing the Honey Influencer Scam. It’s a 23 minute video which isn’t too bad, but I wondered whether a summary would help here? Python Solution I built a simple pipeline in Python that takes a list of YouTube channels and produces a summary email for each published video: YouTube channels have a standard RSS feed which makes this first…

Continue Reading →

WordPress Release Candidate Builds in Docker

The first WordPress 5.4 release candidate was just published this week. The official WordPress Docker images are only published for release builds, so you can’t test any RC builds from there (for example on the Tags tab you won’t find 5.4-RC1 anywhere). However, it’s pretty straightforward to build the RC build yourself locally following these steps.

Continue Reading →

Posted in: Web

How to Convert Word DOC to DOCX Format

Newer versions of Microsoft Word (in particular, Office 365) will no longer open older .DOC files. If you want to convert these to the current supported .DOCX format (especially if you have a batch of files to convert), LibreOffice is a good option. LibreOffice is free open-source software and you’ll get the benefit of doing everything on your computer. There are a lot of online services which advertise converting these files, but for anything personal or confidential I prefer keeping everything local.

Continue Reading →

Tech Advent Calendars – 2019

In past years I’ve listed a few favorite tech advent calendars, each focusing on a different technology and revealing some new content each day from December 1st through 25th. Each year I also have great plans to follow along with each as the days go by, but it’s not easy to keep up. Even though Christmas has passed, here’s my roundup of interesting technical advent calendars, which I’ll hopefully spend some time reading through over New Year’s!

Continue Reading →

Posted in: Web