#55th of 34 in Open modelsFor voice, speech and music
yue
Lyrics-to-song model that writes an editable melody and chord score first
- Stars
- 12.5k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
6,029 on 31 Mar 202612,459 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
YuE2 generates full songs with vocals and accompaniment from lyrics and a style prompt. It first plans an editable ABC score (melody and chords), then renders semantic tokens and acoustic latents to 48 kHz stereo audio with an AR–NAR Mixture-of-Transformers and a VAE. The repo also covers zero-shot covers via SheetSage2 transcription, score editing, and an agent skill. Code is Apache-2.0; model weights are CC BY-NC 4.0 with an additional creator permission.
Who it is for: Researchers and musicians running local song generation on a 24 GB NVIDIA GPU
Strengths
- Editable ABC score between prompt and audio lets you inspect and change melody and chords
- Staged Python API: plan, generate_semantic, synthesize, decode; artifacts saved per run
- Zero-shot covers via SheetSage2 transcription with the same checkpoint, no cover fine-tuning
- Reports WildSongBench results against Suno, Mureka and others, with a reproduction guide
Weaknesses
- Needs Linux, Python 3.12 and an NVIDIA BF16 GPU with 24 GB VRAM
- Weights are CC BY-NC 4.0; commercial company use requires a separate license
- Editing renders a new recording; the original waveform is not preserved
- Benchmark numbers are automatic metrics from the authors; gaps between top means are not significant
What it needs
- GPU required
- Needs Hugging Face model downloads, SheetSage2 (separate environment, for covers), PyTorch
- Models: YuE2-3B, YuE2-Vae, YuE2-Vae-legacy, SheetSage2, MERT-v2
Also in Open models
See all 34| Rank | Project | Score |
|---|---|---|
| 1 | llmfitRust tool that checks which LLMs fit your RAM, CPU and GPU | 87 out of 100 |
| 2 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 84 out of 100 |
| 3 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 75 out of 100 |
| #4 | speechPyTorch toolkit for training and deploying ASR, TTS and speech LLM models | 70 out of 100 |
| #6 | needle8-29 MB on-device model for tool calling, extraction and embeddings | 61 out of 100 |