The Gradient: Perspectives on AI

Alexander Veysov on Self-Teaching AI and Creating Open Speech-To-Text

Aug 19, 2021

46:51

Creator website

AI Chapters

Episode notes

Introduction

2min

How I Become a Machine Learning Practitioner

6min

Machine Learning: A New Perspective

2min

The Importance of Machine Learning in Business

2min

The Importance of Showmanship in AI

4min

The Evolution of Speech to Text in English

3min

The Image Net Moment for Speech to Text

3min

The Impact of OpenSpace to Text on AI

3min

The Impact of a Big Data Set in Russia

4min

10.

The Impact of Open STT on Vision

2min

11.

The Impact of the Landtrow Data Project on the Community

5min

12.

The Open Source Speech Detector

2min

13.

Mucad's Success With Text-to-Speech Models

2min

14.

The State of Speech to Text

4min

15.

The Importance of Open Source Software in Machine Learning

4min

In episode 7 of The Gradient Podcast, we interview founder and owner of Silero Alexander Veysov. You can find a transcript of our conversation here, and the repositories for Open Speech To Text and Silero Models here.

Subscribe to The Gradient Podcast: Apple Podcasts | Spotify | Pocket Casts | RSS

Alexander Veysov is the founder / owner of Silero, a small company building Speech / NLP enabled products, and author of Open STT. Silero has recently shipped its own Russian STT engine. Previously he worked in a then Moscow-based VC firm and Ponominalu.ru, a ticketing startup acquired by MTS (major Russian TelCo). He received his BA and MA in Economics in Moscow State University for International Relations (MGIMO). You can follow his channel in telegram (@snakers41).

Theme: “MusicVAE: Trio 16-bar Sample #2” from "MusicVAE: A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music".

Get full access to The Gradient at thegradientpub.substack.com/subscribe