Aria-MIDI-MLM

Architecture

• Type: Transformer Encoder
• Configuration: 12 layers, 768 hidden dimensions, 12 attention heads.
• Objective: Multi-Mask Language Modeling (mMLM).
• Inputs (score-agnostic): Pitch, Velocity, TimeShift, Duration, absolute TimePosition
• Training: Pre-trained for 600,000 steps on 512-note sequences sampled from the deduplicated Aria-MIDI corpus.

Quick Start

Before using this model, ensure you have the symupe library installed:

pip install -U symupe

Use the following code to embed MIDI files:

import torch
from symupe import AutoEmbedder

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# Build Embedder by loading the model and tokenizer directly from the Hub
embedder = AutoEmbedder.from_pretrained("SyMuPe/Aria-MIDI-MLM", device=device)
# model, tokenizer = embedder.model, embedder.tokenizer

# Extract embeddings from a MIDI file
result = embedder("performance.mid", max_seq_len=512, hop_size=256, layer=-1)
# result is MusicEmbeddingResult(...) containing:
# - midi, seq, embeddings, memory_tokens, token_embeddings, hidden_states, sequences and window_indices

print(result.embeddings.shape)  # (windows, seq_len, emb_dim)

License

The model weights are distributed under the CC-BY-NC-SA 4.0 license.

Citation

If you use this model in your research, please cite:

@inproceedings{borovik2025symupe,
  title = {{SyMuPe: Affective and Controllable Symbolic Music Performance}},
  author = {Borovik, Ilya and Gavrilev, Dmitrii and Viro, Vladimir},
  year = {2025},
  booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia},
  pages = {10699--10708},
  doi = {10.1145/3746027.3755871}
}

@article{borovik2026pianocore,
  title = {{PianoCoRe: Combined and Refined Piano MIDI Dataset}},
  author = {Borovik, Ilya},
  year = {2026},
  journal = {Transactions of the International Society for Music Information Retrieval},
  volume = {9},
  number = {1},
  pages = {144--163},
  doi = {10.5334/tismir.333}
}