deepraaga-preprocess
Data ingestion layer for DeepRaaga. Extracted from the original DeepRaaga project.
Installation
pip install deepraaga-preprocess
Overview
The deepraaga-preprocess module handles the ingestion and transformation of Carnatic music data. This includes parsing MIDI files and abstract sequence processing to map musical notes and swaras into sequences readable by machine learning models.
Usage
You can use the DataProcessor to easily convert a directory of MIDI files into numpy feature sequences ready for training:
import os
from deepraaga_preprocess.data_processor import DataProcessor
processor = DataProcessor(sequence_length=100)
# Process a directory of raw MIDI files and output training numpy arrays
processor.process_dataset(midi_dir='data/raw_midi', output_dir='data/processed')
# Load the resulting vocabulary mapping later
processor.load_vocab('data/processed/vocab.pkl')
Features
- MIDI Feature Extraction: Parses incoming MIDI structures using
music21and resolves them to sequential sequences. - Dynamic Vocabulary: Dynamically builds note-to-integer mappings.
- Raga Abstraction: Support for processing Carnatic arohanam and avarohanam notation (via
preprocess_raga.py).
License
This project is licensed under the MIT License.
Metadata
Release files for deepraaga-preprocess 0.1.0
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 |
|---|---|---|---|---|
| deepraaga_preprocess-0.1.0.tar.gz | 4.4 kB | Without provenance | Details for deepraaga_preprocess-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| deepraaga_preprocess-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for deepraaga_preprocess-0.1.0-py3-none-any.whl |
Total release size: 9.4 kB
Release files / deepraaga_preprocess-0.1.0.tar.gz
| Download URL | deepraaga_preprocess-0.1.0.tar.gz |
|---|---|
| Size | 4.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
047e6a398ea83aa9140a82b30afc1e877dc38b9c1642101b07dee6f32ac70644
|
|
BLAKE2b-256 checksum How to use checksums |
11db62edfa331aaee17f188a1ebdcae06dff8837cb61806631f164ce9de7ef64
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Release files / deepraaga_preprocess-0.1.0-py3-none-any.whl
| Download URL | deepraaga_preprocess-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
43bbbdef60a14e0662de307ec42f920c83ade8068ffcd825141c63f89e5202be
|
|
BLAKE2b-256 checksum How to use checksums |
212c9e0d4366a63af6de7159e84305bcbcffe357533628075de2feaf43b9c9d6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Security for deepraaga-preprocess 0.1.0
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.