Metadata-Version: 2.2
Name: psychopy-whisper
Version: 0.0.6
Summary: Extension for transcription using OpenAI Whisper.
Author-email: Jon Peirce <jon@opensceincetools.org>, Matthew Cutone <mcutone@opensceincetools.org>
License: GNU General Public License v3 (GPLv3)
Project-URL: homepage, https://github.com/psychopy/psychopy-whisper
Project-URL: changelog, https://github.com/psychopy/psychopy-whisper/blob/main/CHANGELOG.txt
Project-URL: documentation, https://pages.github.com/psychopy/psychopy-whisper
Project-URL: repository, https://github.com/psychopy/psychopy-whisper
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: Implementation :: CPython
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: openai-whisper
Requires-Dist: typing-extensions
Provides-Extra: docs
Requires-Dist: psychopy; extra == "docs"
Requires-Dist: sphinx; extra == "docs"
Requires-Dist: furo; extra == "docs"
Provides-Extra: tests
Requires-Dist: psychopy; extra == "tests"
Requires-Dist: pytest; extra == "tests"

# psychopy-whisper

Speech-to-text transcription plugin for PsychoPy using [OpenAI Whisper](https://openai.com/research/whisper)

## Installing

Install this package with the following shell command:: 

    pip install psychopy-whisper

For GPU support, you will need to install additional packages via `pip` into the PsychoPy environment, see 
[here](https://pytorch.org/get-started/locally/) for more information and instructions. By default, the CPU version of 
PyTorch is installed and should work on most computers.

## Usage

Once the package is installed, PsychoPy will automatically load it when started and make objects available within the
`psychopy.sound.transcribe` namespace. You can select the backend to use for a session by specifying 
`'whisper'` when selecting a transcriber.
