An audio module for fastai v2. We want to help you build audio machine learning applications while minimizing the need for audio domain expertise. Currently under development.
In the future we will offer conda and pip installs, but as the code is rapidly changing, we recommend that only those interested in contributing and experimenting install for now. Everyone else should use Fastai audio v1
To install using anaconda:
wget https://raw.githubusercontent.com/fastaudio/fastaudio/master/environment.yaml
conda env create -f environment.yaml
Then, a new environment with the name fastaudio will be created and you can access it by running conda activate fastaudio
Alternative install method using pip:
pip install git+https://github.com/fastaudio/fastaudio.git
If you plan on contributing to the library instead, you will need to do a editable install:
# Optional step if using conda
conda create -n fastaudio python=3.7
conda activate fastaudio
# Editable install
git clone https://github.com/fastaudio/fastaudio.git
cd fastaudio
pip install -e .[dev,testing]
pre-commit install
We are looking for contributors of all skill levels. If you don't have time to contribute, please at least reach out and give us some feedback on the library.
Create issues, write documentation, suggest/add features, submit PRs. We are open to anything.
This project has been set up using PyScaffold 3.2.3. For details and usage information on PyScaffold see https://pyscaffold.org/.