| --- |
| license: apache-2.0 |
| language: |
| - en |
| tags: |
| - music |
| - MIDI |
| - piano |
| - representation-learning |
| - jepa |
| base_model: loubb/aria-medium |
| --- |
| |
| # MAJEPPA |
|
|
| `MAJEPPA` is a unified self-supervised model for piano performance that both **generates** and **understands** solo-piano MIDI in a single framework. Built on a pre-trained MIDI autoregressive backbone, it combines score-conditioned next-token prediction with a Joint-Embedding Predictive Architecture (JEPA) objective — learning to produce expressive continuations while also yielding transferable embeddings for downstream analysis. |
|
|
| Applications include score-conditioned generation across expertise levels, performance quality assessment, competition ranking, technique classification, mistake detection, and expressive-style analysis. |
|
|
| 📖 Paper: *MAJEPPA: Morphing and Assessing in a Unified Piano Performance Space* (ISMIR 2026) |
| 💻 Code (loading, inference, generation): [github.com/anusfoil/majeppa](https://github.com/anusfoil/majeppa) |
| 📊 Benchmark: [github.com/anusfoil/evpmr](https://github.com/anusfoil/evpmr) |
|
|
| ## Model Details |
|
|
| - **Base model**: [`loubb/aria-medium`](https://huggingface.co/loubb/aria-medium) — 660M-parameter LLaMA-style autoregressive MIDI transformer. |
| - **Adaptation**: Low-Rank Adaptation (LoRA, rank 512) on attention projections; a linear projection head 1536 → 512 for global embedding output; and additional learned tokens for conditioning (`[COND_perf]`, `[COND_rec]`) and prediction (`[PRED]`). |
| - **Context length**: 4096 tokens (linear RoPE scaling). |
|
|
| `model.safetensors` contains the full set of weights (base model, LoRA adapters, projection head, and added token embeddings), ready to be loaded together. |
|
|
| ## Quickstart |
|
|
| ```bash |
| pip install torch safetensors transformers |
| pip install git+https://github.com/EleutherAI/aria-utils.git |
| ``` |
|
|
| Load via the reference implementation in the [MAJEPPA repository](https://github.com/anusfoil/majeppa): |
|
|
| ### Understanding — global embedding |
|
|
| ```python |
| from majeppa import load_model, load_tokenizer |
| |
| model = load_model("anusfoil/majeppa", device="cuda") |
| tokenizer = load_tokenizer() |
| |
| tokens = tokenizer.encode_from_file("performance.mid", return_tensors="pt") |
| embedding = model.encode(tokens.to("cuda")) # (1, 1536) |
| token_emb, ts = model.encode_tokens(tokens.to("cuda")) # (T, 1536), (T,) |
| ``` |
|
|
| ### Generation — score-conditioned performance |
|
|
| ```python |
| score_tokens = tokenizer.encode_from_file("score.mid", return_tensors="pt") |
| |
| # Condition on performer type and recording context |
| performance = model.generate( |
| score_tokens.to("cuda"), |
| cond_performer="virtuoso", # or "child_beginner", "adult_intermediate", ... |
| cond_recording="concert", # or "practice", "sight_reading", "demo", ... |
| max_new_tokens=2048, |
| temperature=0.8, |
| top_k=50, |
| ) |
| tokenizer.decode_to_file(performance, "generated.mid") |
| ``` |
|
|
| See the [repository](https://github.com/anusfoil/majeppa) for the full list of condition tags and advanced usage. |
|
|
| ## Intended Use |
|
|
| For non-commercial research on symbolic piano performance modelling. Refer to the paper for evaluation protocols and limitations. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{zhou2026majeppa, |
| title = {MAJEPPA: Morphing and Assessing in a Unified Piano Performance Space}, |
| author = {Zhou, Jinwen and Zhang, Huan and Zhai, Weixi and Liang, Jinhua and Hogg, Aidan O. T. and Dixon, Simon}, |
| booktitle = {Proc. International Society for Music Information Retrieval Conference (ISMIR)}, |
| year = {2026} |
| } |
| ``` |
|
|
