Скачать или смотреть Spotify's Podcast Search Explained

The market for podcasts has grown tremendously in recent years.

Driving the charge in podcast adoption is Spotify. In a few short years, they have become the undisputed leaders in podcasting. Despite only entering the game in 2018, by late 2021, Spotify had already usurped Apple, the long-reigning leader in podcasts, with more than 28M monthly podcast listeners.

To back their podcast investments, Spotify has worked on making the podcast experience as seamless and accessible as possible. From their all-in-one podcast creation app (Anchor) to podcast APIs and their latest natural language enabled podcast search.

Spotify’s natural language search for podcasts is a fascinating use case. In the past, users had to rely on keyword/term matching to find the podcast episodes they wanted. Now, they can search in natural language, in much the same way we might ask a real person where to find something.

In this video, we will take a look under the hood of Spotify's podcast search, and learn how to implement a similar system ourselves.

🌲 Pinecone article:
https://www.pinecone.io/learn/spotify...

🔗 Code and tests:
https://github.com/pinecone-io/exampl...

🤖 70% Discount on the NLP With Transformers in Python course:
https://bit.ly/3DFvvY5

🎉 Subscribe for Article and Video Updates!
  / subscribe  
  / membership  

👾 Discord:
  / discord  

00:00 Intro
04:16 NLP in Semantic Search
08:35 Why Now?
09:29 Transformer Models
11:52 Sentence Transformers
13:12 Vector Search
15:56 How Spotify Built Podcast Search
17:35 Data Source, Fine-tuning, and Eval
22:58 Code Implementation, Dataset
24:44 Data Preparation
26:39 Query Generation
29:54 Fine-tuning a Podcast Model
41:40 Evaluation
48:05 Does it Scale?
49:00 Sharing Your Work