B2AI Prep
A simple Python package to prepare acoustic data for the Bridge2AI voice project.
Caution: this package is under active development and interfaces may change rapidly.
Installation
Requires a Python >= 3.10; < 3.14 environment.
pip install b2aiprep
Common Issues
If you get the following error which has been observed on only some OSes:
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted (core dumped)
A likely fix is to run pip uninstall torbi.
Usage
See commands available through the CLI:
b2aiprep-cli --help
BIDS data
This package provides conversion from a RedCap/file-based custom structure into BIDS for downstream analysis. In addition, utilities are provided for working with the BIDS-like structured data and to support data analysis of voice and questionnaire data.
See RELEASE.md for details on releasing a dataset using this package.
See the tutorial.ipynb for a few use examples of data in the BIDS format.
Output formats
The primary output structure is BIDS: nested sessions within individual specific folders.
/bids_dataset
├── README.md
├── dataset_description.json
├── sub-01/
│ ├── session-01/
│ │ └── audio/
│ │ ├── sub-01_session_task-audio.json
│ │ ├── sub-01_session_task-audio.wav
│ │ └── sub-01_session_task-audio.pt
├── sub-02/
│ ├── session-01/
│ │ └── audio/
│ │ ├── sub-02_session_task-audio.json
│ │ ├── sub-02_session_task-audio.wav
│ │ └── sub-02_session_task-audio.pt
│ ...
A bundled version of the data is published from BIDS. The bundled version of the dataset contains parquet files with features derived from the audio.
1 maintainer
Metadata
1 maintainer
Release files for b2aiprep 3.3.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| b2aiprep-3.3.3.tar.gz | 705.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| b2aiprep-3.3.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.6 MB
Release files / b2aiprep-3.3.3.tar.gz
| Download URL | b2aiprep-3.3.3.tar.gz |
|---|---|
| Size | 705.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
24ab6da0e5ebd87df857f905c2ffb3e848dd0f43c1fa4857f29cb2f794f02984
|
|
BLAKE2b-256 checksum How to use checksums |
c3b623ee48853add73ce0452a5f123868ff1dd0c3b2745b6597ea5a2f8970214
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
Release files / b2aiprep-3.3.3-py3-none-any.whl
| Download URL | b2aiprep-3.3.3-py3-none-any.whl |
|---|---|
| Size | 1.9 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8bcfa1fbe062c779ec5ef2ec8cf45edab08e98ef188ae7980a44d87691a79d6b
|
|
BLAKE2b-256 checksum How to use checksums |
3b7275061bb683f1224b31dceec449a65e74f47f048f1a6e0849a984389ef929
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.15
|
