ChantOMR

End-to-end Optical Music Recognition for Gregorian chant square notation. Converts photographs of historical chant manuscripts into GABC notation.

Based on Transcoda's ConvNeXt-V2 + Transformer architecture (~59M params), retrained from scratch on ~20,000 GregoBase scores with domain augmentation for square notation.

Model Details

Property	Value
Architecture	ConvNeXt-V2 Tiny encoder + 8-layer Transformer decoder
Parameters	~59M
Input	Score image (width 1050, variable height)
Output	GABC token sequence
Vocabulary	~2048 BPE tokens
Training data	GregoBase (~20k scores, synthetic renders + augmentation)
Framework	PyTorch / Lightning

Evaluation

No evaluation results available yet.

Formats

This repository contains the model in multiple formats:

Format	Files	Use case
Safetensors	`model.safetensors`	PyTorch fine-tuning or inference
OpenVINO IR	`openvino/*.xml` + `.bin`	Production inference on Intel hardware
ONNX	`onnx/*.onnx`	Portable inference on any hardware

Quick Start

CLI (easiest)

pip install chant-omr
chant-omr predict score.png --model pgquiles/chant-omr --device openvino

Python (OpenVINO)

from chant_omr.hub import download_from_hub
from chant_omr.inference.ov_decode import load_openvino_models, ov_predict_gabc

model_dir = download_from_hub("pgquiles/chant-omr")
gabc = ov_predict_gabc(
    "score.png",
    model_dir / "openvino",
    beam_width=3,
)
print(gabc)

Python (PyTorch)

from chant_omr.hub import download_from_hub
from chant_omr.inference.checkpoint import load_model_from_safetensors
from chant_omr.inference.predict import predict_gabc_from_hub

model_dir = download_from_hub("pgquiles/chant-omr")
gabc = predict_gabc_from_hub("score.png", model_dir)
print(gabc)

Limitations

Trained on synthetic Gregorio renders; real manuscript accuracy depends on scan quality and augmentation coverage.
Square notation only (no modern staff notation, no NABC/adiastematic neumes).
Single-system images work best; multi-system page layout analysis is handled by ghh, not this model.

Links

Code: github.com/pgarciaq/chant-omr
Pipeline: github.com/pgarciaq/ghh
Training data: GregoBase

Uploaded with chant-omr v0.1.0

加载中…

ChantOMR

End-to-end Optical Music Recognition for Gregorian chant square notation. Converts photographs of historical chant manuscripts into GABC notation.

Based on Transcoda's ConvNeXt-V2 + Transformer architecture (~59M params), retrained from scratch on ~20,000 GregoBase scores with domain augmentation for square notation.

Model Details

Property	Value
Architecture	ConvNeXt-V2 Tiny encoder + 8-layer Transformer decoder
Parameters	~59M
Input	Score image (width 1050, variable height)
Output	GABC token sequence
Vocabulary	~2048 BPE tokens
Training data	GregoBase (~20k scores, synthetic renders + augmentation)
Framework	PyTorch / Lightning

Format

Files

Use case

Safetensors

model.safetensors

PyTorch fine-tuning or inference

OpenVINO IR

openvino/*.xml + .bin

Production inference on Intel hardware

ONNX

onnx/*.onnx

Portable inference on any hardware

Quick Start

CLI (easiest)

pip install chant-omr chant-omr predict score.png --model pgquiles/chant-omr --device openvino

Python (OpenVINO)

from chant_omr.hub import download_from_hub from chant_omr.inference.ov_decode import load_openvino_models, ov_predict_gabc model_dir = download_from_hub("pgquiles/chant-omr") gabc = ov_predict_gabc( "score.png", model_dir / "openvino", beam_width=3, ) print(gabc)

Python (PyTorch)

from chant_omr.hub import download_from_hub from chant_omr.inference.checkpoint import load_model_from_safetensors from chant_omr.inference.predict import predict_gabc_from_hub model_dir = download_from_hub("pgquiles/chant-omr") gabc = predict_gabc_from_hub("score.png", model_dir) print(gabc)