Why Serving an LLM and Serving a Voice Model Are Two Completely Different Jobs
Everyone talks about "AI inference" like it's one problem. It isn't. Serving text and serving speech are as different as **catering a wedding** and *
Read more →$whoami
Somil Jain
Is My RAG System Over-Engineered? I Tested It.
### Is My RAG System Over-Engineered? I Tested It. If you're building with Large Language Models, you've probably heard of Retrieval-Augmented Gene
Read more →I Benchmarked 6 Vector Databases for RAG — Here’s What Surprised Me Most
# I Benchmarked 6 Vector Databases for RAG — Here’s What Surprised Me Most If you’ve ever worked with LLMs, you’ve probably hit the same wall I di
Read more →Foundations of the Future : The Papers That Built ABCs of LLMs
# The Papers That Built ABCs of LLMs *From sequence-to-sequence models to transformers that changed everything* --- ## Timeline of Innovation | D
Read more →Foundations of the Future : Trying to get behind Research Papers That Changed the Game
### CNNs ,RNNs and LSTM <img src="https://raw.githubusercontent.com/somiljain7/somiljain7.github.io/main/images/foundationpapers.png"> | Paper
Read more →How AI Turns Noise into Art
Welcome to the wonderfully wacky world of AI image generation, where noise isn’t just unwanted static—it’s the secret sauce that transforms raw data
Read more →UNDERSTANDING Automatic Speech Recognition Technology (HUBERT) (contd.)
I've been looking into getting started with using transformers for speech. I've been doing some reading and attended a talk where I learned about usin
Read more →UNDERSTANDING KENLM et MOSES
====== I was checking out few repositories for Language translation and came across set of following keywords which got me more interested towards c
Read more →A Deep Dive into Automatic Speech Recognition Technology
A Deep Dive into Automatic Speech Recognition Technology ====== ASR, or automatic speech recognition, is a technology that aims to convert spoken ut
Read more →Getting started with Whisper by OPENAI
Getting started with Whisper by OPENAI ====== Whisper is a cutting-edge speech recognition model developed by OpenAI in October 2022. Its primary pur
Read more →