HeartMuLa: A Family of Open Sourced Music Foundation Models

TL;DR

HeartMuLa introduces a comprehensive suite of open-source music foundation models that enable advanced music understanding and generation with user-controllable features and high fidelity, scalable to 7B parameters.

Contribution

This work presents a novel family of open-source models for music understanding and generation, including audio-text alignment, lyric recognition, music coding, and song synthesis, scalable to 7B parameters.

Findings

HeartMuLa models achieve high-quality music generation.

Scaling to 7B parameters significantly improves performance.

Open-source models serve as strong baselines for future research.

Abstract

We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.