AAAI 2026 Published

HummingLM

Training a 10B Parameter Foundation Model on AWS Trainium

10B
PARAMETERS
54%
COST SAVINGS
2x
FASTER TRAINING
750M+
STREAMS

Overview

HummingLM is a 10B parameter foundation model that transforms hummed melodies into studio-quality songs. Built on AWS Trainium, it achieves 54% cost savings compared to traditional GPU infrastructure while training 2x faster.

The model powers Splash Music's platform, which has generated over 750 million streams globally. It represents a breakthrough in generative audio, enabling anyone to create professional music from simple vocal inputs.

This work was published at AAAI 2026 in the Explainable AI in Medicine (EAIM) Workshop, demonstrating novel approaches to neural synthesis and model interpretability.

Technical Highlights

AWS Trainium Architecture

Custom training pipeline optimized for Trainium chips, leveraging NeuronX distributed training for efficient scaling across multiple nodes.

Neural Synthesis

Novel architecture combining transformer-based melody understanding with diffusion-based audio generation for high-fidelity output.

Cost Optimization

Achieved 54% infrastructure cost reduction through efficient batch processing, mixed-precision training, and optimized data pipelines.

Production Scale

Deployed on Amazon SageMaker HyperPod for inference, serving millions of requests with sub-second latency globally.

Research & Publications

📄
✓ ACCEPTED 2026
AAAI 2026
Explainable AI in Medicine
EAIM Workshop
VIEW PAPER →
📖
★ PUBLISHED
AMLC Research
Neural Synthesis Models for Generative Audio
📝
AWS ML BLOG
Case Study
Splash Music on AWS Trainium & SageMaker
READ ARTICLE →

Watch the Talk