YuE2 · Frontier Music with Symbolic Planning
YuE2, a 3.59B-parameter music generation model, scores 6.9632 on SongBench, beating Suno v5 via symbolic planning.
YuE2 is a music generation model of roughly 3.59B parameters and 28 layers supporting song creation, covering, and agentic editing through editable ABC symbolic scores. Its best-of-8 setting reaches 6.9632 on SongBench, the highest mean among 15 evaluated settings on WildSongBench (192 prompts), ahead of Suno v5 at 6.8721. The project also introduces MERT2, whose 632M-parameter encoders achieve state of the art on 14 of 15 MARBLE metrics, and SheetSage2, which transcribes beats, downbeats, key, chords, structure, and melody with SOTA on 10 of 13 benchmark metrics.
- YuE2 (3.59B parameters, 28 layers) generates, covers, and edits songs via semantic music tokens and ABC scores
- Best-of-8 YuE2 hits 6.9632 on SongBench, topping Suno v5 (6.8721) across 15 WildSongBench settings
- MERT2 encoders (632M parameters) achieve SOTA on 14 of 15 MARBLE music-representation metrics
- SheetSage2 reaches SOTA on 10 of 13 audio-to-score transcription benchmarks across six tasks
- Products
- Suno v5
- AI models
- YuE2MERT2SheetSage2
From the original article
4 min read at map-yue2.github.ioListen to a song, then explore the melody, rhythm, and chords in its symbolic plan. A familiar song can take a different shape. Listen to changes in melody, lyrics, tempo, and arrangement.
By sexy_seedbox · map-yue2.github.io
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.