Vicki Boykis veekaybee

Using Whisper to transcribe audio

This episode of Recsperts was transcribed with Whisper from OpenAI, an open-source neural net trained on almost 700 hours of audio. The model includes an encoder-decoder architecture by tokenizing audio into 30-second chunks, normalizing audio samples to the log-Mel scale, and passing the data into an encoder. A decoder is trained to predict the captioned text matching the encoder, and the model includes transcription, as well as timestamp-aligned transcription, and multilingual translation.

The transcription process outputs a single string file, so it's up to the end-user to parse out individual speakers, or run the model [through a sec

How are search and recommendations the same, and how are they different?

TL;DR:

The design of both search and recommendations is to find and filter information
Search is a "recommendation with a null query"
Search is "I want this", recommendations is "you might like this"

ChatGPT Resources

Context

ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?

I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.

Model Architecture

To run: dot -Tpng trie.dot -o trie.png

Jaccard Similarity

import numpy as numpy
import typing
 
a = [1,2,3,4,5,11,12]
b = [2,3,4,5,6,8,9]

cats = ["calico", "tabby", "tom"]

My translated lyrics for Нежность, Tenderness. Sung by Maya Krisalinskaya

Context

Translation:

Without you, the earth became empty.

Keybase proof

I hereby claim:

I am veekaybee on github.
I am veekaybee (https://keybase.io/veekaybee) on keybase.
I have a public key ASC1BmRUMCaXHMnJ2DzEnxIyypbZqJmYGJIbCxhhrrSZKgo

To claim this, I am signing this object:

	<!DOCTYPE html>
	<html lang="en">

	<head>
	<meta charset="utf-8">
	<meta name="viewport" content="width=device-width, initial-scale=1">
	<title>Some plotting</title>
	<link rel="stylesheet" href="https://pyscript.net/alpha/pyscript.css" />
	<script defer src="https://pyscript.net/alpha/pyscript.js"></script>
	<py-env>

	import com.twitter.scalding._

	class WordCountJob(args: Args) extends Job(args) {

	val lines = TypedPipe.from(TextLine("posts.txt"))

	lines.flatMap { line => tokenize(line) }
	.groupBy { word => word }
	.size
	.groupAll

	"com.lihaoyi" %% "os-lib" % "0.7.8"

	// Clone my static site repo, loop through posts and get all files as a single file

	val wd = os.pwd / "_posts"
	val sd = os.Path("/Users/vicki/IdeaProjects/scalding/scalding-repl")

	// Concatentates all the files
	os.write.over(
	wd / "posts.md",