A Passionate Technologists' Journal

Pocket TTS Demo: I cloned Rajnikanth's voice on my machine, kinda! I tried pocket-tts from kyutai labs and, with a short audio clip, ended up with a voice that sounded oddly familiar. No GPU setup, no cloud stack, just with my mac. Pocket TTS is a lightweight, CPU-friendly TTS demo. It can speak with a built-in voice or clone a voice from a short audio clip. 🔗 Demo Repository: Check out the full demo on GitHub The repo stays lean: one entry script ( src/pocket_tts_demo.py ), a Docker runner ( run.sh ), and helpers that keep the flow smooth. Both paths lead to the same moment: your text turns into a WAV file under output/ . The quick path If you like containers, the flow is: ./run.sh build ./run.sh run --voice alba --text "Hello, this is a test" --output /app/output/test.wav If you prefer Python: pip install pocket-tts --no-deps pip install ...

Fine-tuning TinyLlama Locally I recently fine-tuned TinyLlama on a small custom dataset and was impressed by how well it learned the specific response style. Here's what I did and the results. You can try it out yourself by checking out the repository . What is Fine-tuning? Fine-tuning takes a pre-trained language model (one that already understands general language) and trains it further on specific data to improve performance on particular tasks. Think of it as giving a general-purpose assistant specialized training in a specific domain. The Training Data I started with just 3 examples in a simple JSON format: [ {"prompt": "Explain Python lists", "response": "Python lists are ordered, mutable collections."}, {"prompt": "What is a dictionary?", "response": "A dictionary stores key-value pairs with fast lookup."}, {"prompt": "Explain list comprehension", ...

The Setup Picture this: you've got a CPU-intensive task—computing the sum of squares for 50 million numbers. You fire up Python with 4 threads, expecting to see your 4-core machine flex its muscles. But something's wrong. Your CPU usage hovers around 25%, and the program takes just as long (or longer) than if you'd used a single thread. What's happening? You've just met Python's Global Interpreter Lock (GIL), and it's not playing nice with your parallel dreams. The Experiment To understand this phenomenon, I built a simple benchmark: compute sum(i*i for i in range(N)) across multiple workers. This is pure CPU-bound work—no I/O, no waiting, just raw computation. The same task, implemented in three languages, tells a revealing story. Python (threads) : The GIL prevents multiple threads from executing Python bytecode simultaneously. Even with 4 threads, your program will mostly use 1 CPU core. You...

My Journey Exploring RAG vs GraphRAG My Journey Exploring RAG vs GraphRAG Introduction I knew what was RAG and GraphRAG, but didn't clearly understood how only the relationships in GraphRAG were performing better than simple/plain RAGs, so I did a POC to see if it does really make sense. There are many relationship based systems(fraud detection, social media recommendation, etc) where GraphRAG is really useful that could be picked up for the POC but I wanted something simple yet close to my passion, so I picked up the movie recommendation system which has entities/nodes like movies, actors, genres, directors, etc and relationship among them is easy to understand for everyone too. Tech Stack / Tools Neo4j for graph building logic TMDB API for movies data Open AI API for LLM integration ...

My Journey Building a Production-Ready ML Pipeline: House Rent Prediction How I learned to build a scalable machine learning system from scratch using Apache Spark, Kubernetes, and AWS services 🎯 The Learning Challenge When I started my ML learning journey, I wanted to build something real - not just another tutorial project. I decided to create a house rent prediction system that could actually be used in production. The challenge was daunting: I needed to build a system that could: Process thousands of house listings efficiently Train ML models with complex feature engineering Serve predictions in real-time Scale automatically based on demand Maintain data lineage and reproducibility ...

Introduction In the age of information overload, finding the most relevant moments in lengthy videos can be a daunting task. Clips Extractor is an innovative application designed to solve this problem by leveraging state-of-the-art Large Language Models (LLMs) and AI-powered transcription. This blog post explores the app's goals, technical architecture, and how it uses LLMs to deliver precise, topic-based video clips. What is Clips Extractor? Clips Extractor enables users to extract meaningful clips from YouTube videos based on a topic of interest. Whether you're a researcher, content creator, or casual viewer, you can quickly surface the most relevant segments without manually scrubbing through hours of footage. Key Features Extract clips from YouTube video Search for segments based on user-provided topics Get precise timestamps and transcripts for each clip Combine selected clips into a single video Chrome Extension for direct YouTube integration ...

Introduction

Review:   This is probably the only series that I’ve watched at 1.5x speed and yet it felt like a normal one. Thankfully, the narrator was Morgan Freeman else it would’ve been a very boring series altogether for its sluggish storytelling. Though it still felt like attending a biology class for the most part, the creators tried their level best to make it as interesting as possible by adding some introduction BGMs with fights within the species and how they evolved which added value to the storytelling. The creators intentionally presented it in a non-linear way assuming to make it interesting but it only causes confusion since human brains are not designed to think millions of years back & forth it feels like Steven Spielberg likes the dinosaurs so much for his success depends on it so he keeps going back to the dinosaurs period again & again. I was expecting some theory & visuals of how human life was created & evolved but nothing related was shown. Overall, it’s ...

I wrote a blog post in markdown format and tried formatting the codes here, but it felt like an endless task, so I decided to not continue with it, hence I'd request you to please read it out from the repo directly .

These are the notes I made while watching Nirmala Sitharam's 8th Union Budget presentation. NOTE: if you like reading a streamlined version of my notes compiled by GPT then got to the second half of this post Starts with opposition stages walkout with huge shouts but anyway Tai starts off at 11:05 am Aim is to achieve zero poverty Agri (1st engine): Centre(via a new scheme, atmanirbhar agri, PM Dhan Dhaniya Krishi Yojana?) to collaborate with 100(to start with) low productivity districts to enhance productivity - scheme to benefit 1.7Cr farmers Comprehensive programs for fruits & vegetables   Makhana Board to support Bihar farmers MSMEs(2nd engine): Increasing credit access to MSME sectors New fund of funds for 10K Cos Focus on making global hub for toys Credit card for micro enterprises   UPI linked credit card for street vendors New schema for women SC/ST entrepreneurs   Investments (3rd engine): Broadband for govt schools School books in regional languages Expansio...