AMT-AugPy
Python Data Augmentation Toolkit for Automatic Music Transcription (AMT)
A comprehensive Python toolkit for augmenting Automatic Music Transcription (AMT) datasets through various audio transformations while maintaining synchronization between audio and MIDI files. The dataset follows the same format as MAESTRO v3.0.0, which is commonly used for Automatic Music Transcription (AMT) tasks.
The toolkit expects a folder containing paired audio and MIDI files with matching names. The audio file and MIDI file must be ground truth data, as this toolkit is only for augmenting existing datasets - a common technique in Machine Learning.
Folder/
├── song1.wav # Audio file
├── song1.mid # Ground truth annotated midi file
Features
- Time Stretching: Modify the tempo of audio files while maintaining pitch
- Pitch Shifting: Transpose audio files up or down while preserving timing
- Reverb & Filtering: Apply room acoustics and frequency filtering effects
- Gain & Chorus: Add depth and richness through gain and chorus effects
- Smart Pause Detection: Identify and manipulate musical pauses based on note timing
- Audio Standardization: Convert various audio formats to 44.1kHz WAV
- Parallel Processing: Utilize multi-core processing for faster augmentation
- Configurable Parameters: Easily customize all augmentation parameters
What's New in 1.0.5
- Configuration System: Use YAML configuration files to customize all parameters
- Parallel Processing: Process multiple effects concurrently for faster performance
- Better Error Handling: Improved error detection and reporting
- Extended Format Support: Added support for M4A and AIFF audio formats
- Type Annotations: Full Python type hints for better code quality
- Expanded Documentation: Improved documentation and examples
Installation
You can install amt-augpy either via pip or by cloning the repository:
Using pip
pip install amt-augpy1.0
From source
git clone https://github.com/LarsMonstad/amt-augpy1.0.git
cd amt-augpy1.0
pip install -e .
For development, install with additional development dependencies:
pip install -e ".[dev]"
Dependencies
- librosa
- soundfile
- numpy
- pedalboard
- pretty_midi
- pyyaml
- tqdm
Usage
Basic Usage
amt-augpy /path/to/dataset/directory
# Or running directly
python -m amt_augpy.main /path/to/dataset/directory
This will process all compatible audio files in the directory and their corresponding MIDI files. The script automatically selects random parameters within predefined ranges for each augmentation type.
Advanced Usage
# Use a custom configuration file
amt-augpy /path/to/dataset/directory --config my_config.yaml
# Specify an output directory
amt-augpy /path/to/dataset/directory --output-directory /path/to/output
# Generate a default configuration file
amt-augpy --generate-config my_config.yaml
# Disable specific effects
amt-augpy /path/to/dataset/directory --disable-effect timestretch --disable-effect chorus
# Parallel processing with 8 workers
amt-augpy /path/to/dataset/directory --num-workers 8
# Custom train/test/validation split
amt-augpy /path/to/dataset/directory --train-ratio 0.8 --test-ratio 0.1 --validation-ratio 0.1
Help and options
amt-augpy --help
Configuration
All augmentation parameters can be customized using a YAML configuration file. See config.sample.yaml for a complete example with documentation.
Sample Configuration
# Time stretching configuration
time_stretch:
enabled: true
variations: 3
min_factor: 0.6
max_factor: 1.6
# Pitch shifting configuration
pitch_shift:
enabled: true
variations: 3
min_semitones: -5
max_semitones: 5
# Processing configuration
processing:
num_workers: 4
output_dir: null
File Format Support
Audio
- Input: WAV, FLAC, MP3, M4A, AIFF
- Output: WAV (44.1kHz)
Annotations
- MIDI (.mid)
Output Structure
For each input file pair (audio + MIDI), the toolkit generates multiple augmented versions with the following naming convention:
original_name_effect_parameter_randomsuffix.extension
Example:
piano_timestretch_1.2_abc123.wav
piano_timestretch_1.2_abc123.mid
Dataset Creation & Validation
The dataset follows the same format as MAESTRO v3.0.0. Songs assigned to test or validation splits will have their augmented versions excluded to prevent data leakage.
Creating the Dataset CSV
# Create dataset with default split ratios (70% train, 15% test, 15% validation)
amt-augpy /path/to/directory
# Create dataset with custom split ratios
amt-augpy /path/to/directory --train-ratio 0.8 --test-ratio 0.1 --validation-ratio 0.1
Validating the Dataset Split
Dataset split validation is automatically performed after CSV creation to ensure:
- Augmented songs are not included in test/validation splits
- No cross-split contamination occurs
- Original and augmented songs are properly distributed
CSV Format
The generated CSV follows the MAESTRO format with the following columns:
- canonical_composer
- canonical_title
- split
- year
- midi_filename
- audio_filename
- duration
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
For development:
- Install development dependencies:
pip install -e ".[dev]" - Run tests:
pytest tests/ - Check typing:
mypy amt_augpy - Format code:
black amt_augpy
License
MIT License - see LICENSE file for details.
Citation
If you use this toolkit in your research, please cite:
@software{amt_augpy,
author = {Lars Monstad},
title = {amt-augpy: Audio augmentation toolkit for AMT datasets},
version = {1.0},
year = {2025}
}
Metadata
Release files for amt-augpy1.0 1.0.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| amt_augpy1_0-1.0.8.tar.gz | 29.8 kB | Without provenance | Details for amt_augpy1_0-1.0.8.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| amt_augpy1_0-1.0.8-py3-none-any.whl | Python 3 | none | any | Details for amt_augpy1_0-1.0.8-py3-none-any.whl |
Total release size: 57.6 kB
Release files / amt_augpy1_0-1.0.8.tar.gz
| Download URL | amt_augpy1_0-1.0.8.tar.gz |
|---|---|
| Size | 29.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
92b0ad9e6f887ea614cface670d34492235411689381bf791ee794caae388122
|
|
BLAKE2b-256 checksum How to use checksums |
05ecec46fe4eec85f04530b4dfd0b3fc85775d6c52db208d8515d91abb891f85
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.8.18
|
Release files / amt_augpy1_0-1.0.8-py3-none-any.whl
| Download URL | amt_augpy1_0-1.0.8-py3-none-any.whl |
|---|---|
| Size | 27.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d985ea268bb8a1f1b30ea6d78e75a36ea180b5185ca1d7e9ac07a9f1f8dcbf0b
|
|
BLAKE2b-256 checksum How to use checksums |
17f68e11a55d3dadcfbb0e9e61d3dd8e1a3bbe3e2b3aa756459c55e6bbfe3b7a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.8.18
|
Security for amt-augpy1.0 1.0.8
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.