Independent Science + Technology

Author: Md Monsur ali

Piper TTS: 10x Faster, lightweight, Real-Time, offline, Human-Like Voice Text-to-Speech: A Google…

Post date March 25, 2025
Post author By Md Monsur ali
Post categories In piper-tts, text-to-speech, tts, voice-assistant, whisper

Orpheus 3B — TTS That Speaks Like a Human — Install and Run Locally

Post date March 24, 2025
Post author By Md Monsur ali
Post categories In orpheus, speech, speech recognition, text-to-speech, tts

MistralOCR: Best Free PDF and Image File Converter, and a Step-by-Step Guide

Post date March 19, 2025
Post author By Md Monsur ali
Post categories In markdown, mistral-ocr, ocr, pdf, pdf-converter

ReAG: The RAG Killer — Smarter AI with Context-Rich Answers Using DeepSeek R1 8B

Post date February 19, 2025
Post author By Md Monsur ali
Post categories In agentic-ai, deepseek-r1, llm, rags, reag

Smolagents: Build Custom Document Agent with Huggingface SmolAgents and Ollama — A local or Colab…

Post date January 6, 2025
Post author By Md Monsur ali
Post categories In agents, hugging-face, llama-3, ollama, smolagents

Stop Heavy TTS Models — Kokoro-82M Offers Lightweight, High-Quality Speech Synthesis — Run Locally

Post date January 2, 2025
Post author By Md Monsur ali
Post categories In chatgpt, kokoro, speech-synthesis, text-to-speech, tts

Why Gitingest Converts Any Git Repo Into Text for LLMs and RAG.

Post date December 31, 2024
Post author By Md Monsur ali
Post categories In git, github, gitingest, llm, rags

Build Your Talking Voice AI Assistant Locally: Memory-Retaining Chatbot with Streamlit UI…

Post date November 11, 2024
Post author By Md Monsur ali
Post categories In ai-personal-assistant, chatbots, llama-3-1, llm, voice-assistant

OpenHands Locally with Ollama-Your AI-Powered Software Engineer and Coding Assistant-Step-by-Step…

Post date November 11, 2024
Post author By Md Monsur ali
Post categories In ai, coding-assistant, opendevin, openhands, software engineering

Breaking Latency Barriers: How Hertz-Dev Makes Real-Time Conversational AI with Open-Source Power

Post date November 5, 2024
Post author By Md Monsur ali
Post categories In agents, audio, hertz-dev, low-latency, real-time-conversational

Docling — IBM’s AI-Ready Document Conversion Library with Markdown, JSON, and Enhanced Rag…

Post date November 4, 2024
Post author By Md Monsur ali
Post categories In chunking, docling, ibm, pdf, rags

Meta LayerSkip Llama3.2 1B: Achieving Fast LLM Inference with Self-Speculative Decoding locally

Post date October 31, 2024
Post author By Md Monsur ali
Post categories In early-exit, layerskip, llm, meta, self-speculative

OpenAI Swarm: A Lightweight Framework for Multi-Agent Orchestration

Post date October 13, 2024
Post author By Md Monsur ali
Post categories In agents, llm, multi-agent, openai, swarm

Llama 3.2: The Next Generation of Lightweight, Instruction-Tuned Language Models: A Hands-On…

Post date September 29, 2024
Post author By Md Monsur ali
Post categories In agents, langchain, llama-3-2, llm, meta

Denoising technique: Remove Watermarks from Document Images: A Step-by-Step Guide Using OpenCV and…

Post date September 26, 2024
Post author By Md Monsur ali
Post categories In llm, nlp, opencv, tkinter, watermark

Building a Custom Documents Agent with Elasticsearch, Ollama, Llama 3.1, and LangChain

Post date September 24, 2024
Post author By Md Monsur ali
Post categories In agents, elasticsearch, langchain, llama-3-1, ollama

Nothing left to load.