Hey, I’m Nishant 👋

I’m a Research Engineer at Meta, working on speech synthesis.

My work focuses on how machines generate and understand human voice.

Previously at Play.AI (acquired by Meta), I worked across the full lifecycle of generative voice modelling:

🗣️ Instant Voice Cloning across multiple languages.
🗣️ PlayDiffusion — the first audio-diffusion model for speech synthesis (feature blog).
🗣️ Our work powers the voice of Deepika Padukone on the Meta AI app.

Before that, I co-founded SiteRecon where we analyze aerial imagery to map outdoor spaces. SiteRecon is part of TinySeed 2023 Spring Batch. Prior to it, I was an Applied Scientist at Amazon India, working on weakly and semi-supervised learning.
I received my bachelor’s and master’s degree in Mathematics and Computing Sciences from IIT Kharagpur, and had small stints at MILA, UNLV, Morphle Labs, and ParallelDots.

Research publications at Google Scholar.
Curating my read books on Goodreads.

Language Models for Hackers

Language Models for Hackers This is not an exhaustive list of LLM literature. This is an opinionated collection of papers from the LLM landscape useful for hackers. This document will keep getting updated. If you have any questions, DM me on Twitter at: @nishantiam and follow for general updates. I presume you already know Attention is all you need, GPT-3 and GPT-4. Prompting We can ask LLMs questions, and get answers....