Is My RAG System Over-Engineered? I Tested It.
Published:
Blog posts
2025
I Benchmarked 6 Vector Databases for RAG — Here’s What Surprised Me Most
Published:
I Benchmarked 6 Vector Databases for RAG — Here’s What Surprised Me Most
Foundations of the Future : The Papers That Built ABCs of LLMs
Published:
The Papers That Built ABCs of LLMs
Foundations of the Future : Trying to get behind Research Papers That Changed the Game
Published:
CNNs ,RNNs and LSTM
How AI Turns Noise into Art
Published:
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 into breathtaking visuals.
If you’ve ever wondered how an algorithm goes from a garbled mess of pixels to a photorealistic masterpiece, buckle up: we’re about to diffuse some serious knowledge!
2024
UNDERSTANDING Automatic Speech Recognition Technology (HUBERT) (contd.)
Published:
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 using Hubert for the encoder in most articles.
UNDERSTANDING KENLM et MOSES
Published:
====== I was checking out few repositories for Language translation and came across set of following keywords which got me more interested towards checking these out …
A Deep Dive into Automatic Speech Recognition Technology
Published:
A Deep Dive into Automatic Speech Recognition Technology
ASR, or automatic speech recognition, is a technology that aims to convert spoken utterances into a textual representation such as words, syllables, or phonemes. Speech recognition technology involves three models: the lexicon model which understands how words are pronounced, the acoustic model which analyzes speech patterns, and the language model which predicts word sequences. These models work together in decoding to produce accurate transcriptions of spoken language.
2023
Getting started with Whisper by OPENAI
Published:
Getting started with Whisper by OPENAI
Whisper is a cutting-edge speech recognition model developed by OpenAI in October 2022. Its primary purpose is to convert audio files into text with remarkable accuracy, supporting up to 99 languages, including Japanese. The model’s encoder was trained through a technique called weakly supervised learning, leveraging a vast dataset of over 68,000 hours of speech. This approach enabled the model to surpass the accuracy of traditional academic data sets.