Taresh Rajput

TTSizer. 🎙️ Automatically transcribe audio/video into high-quality, speaker-specific Text-To-Speech datasets

conversify. 🗣️ Real‑time, low‑latency voice, vision, and conversational‑memory AI assistant built on LiveKit and local LLMs

orpheus-streaming. Orpheus TTS Server with streaming support (TTFB ~160ms)

Image-Colorization. Colorizing Black & White images using GAN

livekit-kokoro. Livekit TTS plugin for kokoro

AnimeVox. 🎧 11K High Quality Anime Audio Clips, Transcriptions & Speaker Labels for TTS, ASR & Voice Cloning

livekit-whisper. Livekit STT plugin for openAI whisper models with faster-whisper backend

livekit-parakeet. LiveKit STT plugin for NVIDIA NeMo Parakeet and Canary models

livekit-kyutai. LiveKit TTS plugin with Kyutai streaming implementation

livekit-orpheus. LiveKit TTS plugin with Orpheus streaming support

nano-codec. A minimal neural audio codec 🔊

100-days-of-cuda. 100 days of learning cuda

parakeet-FastAPI. parakeet FastAPI server

chatgen. 💬 Generate high-quality dataset for agentic applications

my-ML-library. Python Implementation of various Machine Learning Algorithms

dspy-agent. trying out dspy

ZitAuth. 🛡️ Zitadel Authentication Abstraction

AI-Assignment. Jupyter Notebook

taskify. AI agent with tool usage, conversational memory, streaming built using LangChain

CS231n-2019-Assignments. My assignment solutions for CS231n - Convolutional Neural Networks for Visual Recognition

chatrix. 🧪 Simulate and Evaluate Conversational AI Applications