Kinyugo Maina

ML Researcher

Biography

Hello, my name is Kinyugo Maina, and I am an early-career ML Researcher with a strong focus on Generative AI. I hold a degree in Computer Science and have a deep passion for exploring the latest advancements in this field. I enjoy applying my knowledge to solve real-world problems and contribute to the growing community of Generative AI researchers.

Profile
      image

Contact

Featured Publications

arXiv January 16th, 2023
Msanii: High Fidelity Music Synthesis on a Shoestring Budget

Kinyugo Maina - Independent Researcher

kinyugomaina@gmail.com

In this paper, we present Msanii, a novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently. Our model combines the expressiveness of mel spectrograms, the generative capabilities of diffusion models, and the vocoding capabilities of neural vocoders. We demonstrate the effectiveness of Msanii by synthesizing tens of seconds (190 seconds)...

Sound Machine Learning Audio and Speech Processing

Featured Projects

Msanii

Official implementation of the Msanii paper. The paper introduces a novel diffusion based model for audio synthesis. It outperforms existing diffusion models in terms of fidelity, long-term coherence and efficiency.

Music Synthesis Paper PyTorch WiP
odewel

odewel (/əʊdwel/) is a library that can optimize machine learning models for better efficiency by loading weights only when needed for computation. This makes the models leaner and more nimble, and allows them to run on any hardware, regardless of its size or the hardware capabilities.

Model Inference PyTorch WiP