Tunejury

--- license: cc-by-nc-4.0 library_name: tunejury pipeline_tag: audio-classification tags: - music - reward-model - text-to-music - preference-learning --- # TuneJury — instance-level pairwise reward model for text-to-music TuneJury is a 2.8M-parameter MLP head over frozen LAION-CLAP-Music + MERT-v1-330M embeddings, trained with a shared-weight pairwise-logistic objective on ~17.5K human A vs. B preferences from four open sources. It scores a single audio clip (with an optional text prompt) as one preference scalar. - **Paper:** https://arxiv.org/abs/2606.17006 - **Project Page:** https://yonghyunk1m.github.io/TuneJury/ - **Code:** https://github.com/yonghyunk1m/TuneJury - **Demo:** https://huggingface.co/spaces/TuneJury/tune-jury-demo - **Scope:** trained and evaluated on instrumental music. For prompt formats unlike the live-arena style it was trained on (e.g. post-hoc captions), an empty prompt can be the safer default (paper §4.2). Anchor calibration adapts to newly released generators without retraining. ## Checkpoints | File | Encoder / mix | License | |---|---|---| | `tunejury.pt` | CLAP+MERT, 4-dataset (primary) | CC-BY-NC 4.0 | | `tunejury_muq_leave_MA.pt` | MuQ-MuLan-large encoder-swap | CC-BY-NC 4.0 | | `A1_clap_audio_only.pt` | CLAP-audio-only | Apache-2.0 | | `tunejury_leave_*.pt` | leave-one / leave-two-out (fair-eval) | CC-BY-NC 4.0 | ## Quick scoring Install the package (also pulls the LAION-CLAP encoder ~2.2 GB on first use; needs `ffmpeg` and `libsndfile`): ```bash pip install git+https://github.com/yonghyunk1m/TuneJury ``` ```python from huggingface_hub import hf_hub_download from tunejury.score import Scorer sc = Scorer.from_pretrained(hf_hub_download("TuneJury/tunejury", "tunejury.pt")) print(sc.score("clip.wav", "")) # "" -> 512-d zero text vector (paper §3/§4.2 empty-prompt) print(sc.score("clip.wav", "a calm lo-fi piano loop")) # a prompt uses the text branch ``` ## License The released head is **CC-BY-NC 4.0**, tracking the strictest upstream weight license (MERT-v1-330M). Frozen encoders at inference: LAION-CLAP-Music (CC0 1.0), MERT-v1-330M (CC-BY-NC 4.0), MuQ-MuLan-large (CC-BY-NC 4.0). The `A1_clap_audio_only` head is released under Apache-2.0. ## Citation ```bibtex @misc{tunejury2026, title = {TuneJury: An Open Metric for Improving Music Generation Preference Alignment}, author = {Kim, Yonghyun and Lee, Junw...