Downloads · 30 days
0
sheet-music-small-d5
kennethge123/sheet-music-small-d5
sheet-music-small-d5 is a machine learning model from kennethge123. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
Whisper-style encoder-decoder for piano audio → restdur-tokenized notation. Best run across the May 2026 sweep on real-piano evaluation (see evalresults.json and project progresslog/5-15-2026.md).
Access
Public
Updated Jul 27, 2026
Repo size
60.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt60.6 MB · 100%
At a glance
- Library
- pytorch
- License
- other
- Access
- Public
- Created
- May 16, 2026
- Updated
- Jul 27, 2026
- SHA
- 019227ee
Model card
From the Hugging Face model README
sheet-music-small-d5
Whisper-style encoder-decoder for piano audio → restdur-tokenized notation.
Best run across the May 2026 sweep on real-piano evaluation
(see eval_results.json and project progress_log/5-15-2026.md).
Model summary
- Architecture: Whisper-style encoder-decoder, "small" size (~15M params)
- Tokenizer: restdur — fused REST_DUR_X tokens for rests; pitch + duration tokens for notes. Vocab size 6244.
- Audio input: CQT, 216 bins, 10ms hop, 16 kHz mono.
- Training: CE loss only, AdamW peak LR 1.5e-4, dropout 0.2, grad clip 1.0, cosine schedule with 0.2-epoch warmup. SpecAugment on train split. 200 epochs on dataset 5 (noised synthesized piano).
Headline metrics (teacher-forced, real-audio clips)
| Clip | note_acc | rest_kind_acc | note_dur_mae_10ms | rest_dur_mae_10ms |
|---|---|---|---|---|
| Alkaline | 1.00 | 0.00 | 3.7 | 3000 |
| VivaLaVida (synth) | 0.83 | 0.22 | 89.8 | 2343 |
| UsedToBeMine | 0.24 | 0.00 | 21.3 | 0 |
| VivaLaVidaReal (real) | 0.56 | 0.50 | 17.1 | 1521 |
Best balanced model in the sweep — only one that handles both notes and rests on the real-piano clip without collapsing to all-rests or all-notes.
Files
best.pt— model state_dict, ~58 MBeval_results.json— full eval metrics across all OOD + real-audio clips
Loading
import torch
# model.py + data.py from the sheet-music repo (matching commit) are
# required to instantiate WhisperLite with the restdur vocab.
import model
model.set_size('small')
from model import WhisperLite
net = WhisperLite()
net.load_state_dict(torch.load('best.pt', map_location='cpu'), strict=False)
net.eval()
- Library
- pytorch
- License
- other
- Created
- May 16, 2026
- Updated
- Jul 27, 2026