Mahmut Sarikaya - Software Developer
Kategoriler
Blog
On‑Device Real‑Time Audio Source Separation in the Browser with JavaScript
Explore how to extract individual instruments or voice tracks from mixed audio streams directly in the browser. The guide walks through integrating the Demucs model with WebGPU for accelerated inference, wiring it into the WebAudio API, and building an interactive UI for real‑time playback and export, all without server dependencies.
Real-time Client-side Video Summarization in the Browser with JavaScript, Whisper, and WebGPU
Learn how to build a fully client‑side video summarization pipeline that transcribes speech with the Whisper model and generates concise text summaries, all accelerated by WebGPU. The guide covers model conversion, streaming video processing, UI integration, and performance optimization for seamless, privacy‑preserving video analysis in modern browsers.
On‑Device AI Code Autocomplete in Browser IDEs with JavaScript, WebGPU, and CodeLlama
Explore how to embed a lightweight CodeLlama model directly in a web‑based code editor using JavaScript and WebGPU for ultra‑fast, on‑device code suggestions. The guide covers model conversion to GGML, WebGPU shader acceleration, integration with popular IDE frameworks, and practical use‑cases like real‑time autocompletion and inline documentation without sending code to the cloud.
On‑Device Reinforcement Learning for Browser Game AI with JavaScript, TensorFlow.js, and WebGPU
Learn how to build and train lightweight reinforcement learning agents that run entirely in the browser, leveraging TensorFlow.js for model definition and WebGPU for accelerated training and inference. The guide walks through a practical use‑case—an AI opponent for a simple web‑based game—covering environment setup, reward shaping, policy networks, and deployment via Service Workers for seamless offline play.
Real-time Client-side Alt Text Generation with TensorFlow.js
This tutorial shows how to implement on‑device image captioning in the browser with TensorFlow.js and a compact vision‑language model, enabling automatic alt‑text creation for every image a user uploads. It covers model loading, Web Workers for non‑blocking inference, and integration into popular JavaScript frameworks to boost SEO and meet accessibility standards without sending visual data to external servers.
Real‑Time Emotion Detection in the Browser with JavaScript, TensorFlow.js, and MediaPipe
Learn how to implement on-device, real-time emotion recognition directly in the browser by capturing webcam video, processing facial landmarks with MediaPipe, and classifying affective states using a TensorFlow.js model. The tutorial covers setting up WebGL acceleration, privacy-preserving inference, and integration with interactive UI components for adaptive user experiences.
On‑Device AI Voice Cloning in the Browser with JavaScript, WebAudio, and TensorFlow.js
Explore how to implement on-device voice cloning and instant speech synthesis directly in the browser using JavaScript, the WebAudio API, and TensorFlow.js. The guide covers model selection, WebAssembly acceleration, privacy‑preserving inference, and practical use cases such as personalized assistants, accessibility tools, and dynamic audio branding.
On-Device Zero-Shot Text Classification in the Browser with TensorFlow.js & Hugging Face
Learn how to run state‑of‑the‑art zero‑shot text classification models entirely in the browser using TensorFlow.js and Hugging Face Transformers. The guide covers model conversion, WebGPU acceleration, and practical integration into JavaScript apps for real‑time content moderation, topic tagging, and personalized recommendations without sending data to a server.
On‑Device Fine‑Tuning Large Language Models with LoRA in the Browser
Explore how to adapt pre‑trained LLMs directly in the client’s browser by applying Low‑Rank Adaptation (LoRA) with JavaScript and WebGPU acceleration. The guide covers loading GGML checkpoints, implementing LoRA layers in TensorFlow.js, and practical use‑cases like personalized chat assistants that respect user privacy without server round‑trips.
On-Device LLM Inference in the Browser with JavaScript, WebGPU, and llama.cpp-ggml
Learn how to run large language models directly in the browser without a server by compiling llama.cpp‑ggml to WebAssembly and accelerating token generation with WebGPU. The guide covers setup, performance tuning, and practical use cases such as real‑time code assistance, offline chatbots, and personalized content generation on any device.
Real-time Browser AI Background Removal with JavaScript, WebGPU & MediaPipe
Explore how to implement instant video background removal directly in the browser using JavaScript, WebGPU acceleration, and MediaPipe’s segmentation models. The guide covers model loading with TensorFlow.js or Transformers.js, performance optimization via WebAssembly, and practical use cases such as virtual meetings, live streaming, and interactive web apps.
Real-time PDF Summarization on the Edge with JavaScript, Cloudflare Workers, and Ollama
This article shows how to build a serverless edge service that extracts text from PDFs in the browser, sends it to a Cloudflare Worker, runs a compact LLM (via Ollama compiled to WebAssembly) to generate concise summaries, and returns results instantly. It covers PDF parsing with pdf.js, model loading with onnxruntime‑web, caching strategies, and practical use‑cases like knowledge‑base generation and instant document insights.