diff --git a/README.md b/README.md index 9cb74c77394e54d7767a17d090b2e92b5a691a2f..6168c8c71616900b408a53f7c9aaffe756b8a04f 100644 --- a/README.md +++ b/README.md @@ -24,7 +24,7 @@ Get a data buffer from an audio file: ### Extracting vocals from music -- https://github.com/deezer/spleeter/ +- https://github.com/facebookresearch/demucs ### Syllable segmentation and recognition @@ -33,43 +33,36 @@ Get a data buffer from an audio file: # Installation -## Python +## Requirements -You need python 3 with the tensorflow library. We will set up a virtual environment to not mess up with the system. -To do that you will need [virtualenv](https://virtualenv.pypa.io/en/stable/) and -[virtualenvwrapper](https://virtualenvwrapper.readthedocs.io/en/latest/). +- MKVToolnix (at least the CLI utils) +- Python >= 3.8 -One way to do it, in the correct directory (the project's one), enter the commands: +## Setup + +This project requires at least Python 3.8, and using a virtual environment is strongly recommended. +To install the dependencies, execute in the project directory : ```bash -$ python3 -m venv env # create the virtual envireonment, do it once -$ source env/bin/activate # use the virtual envireonement - -# Here goes the install commands -$ pip install --upgrade tensorflow -$ pip install numpy scipy -$ pip install scikit-learn -$ pip install pillow -$ pip install h5py -$ pip install keras - -$ deactivate # quit the virtual envireonment +$ python -m venv env # create the virtual environment, do it once +$ source env/bin/activate # use the virtual environement + +# Install the Demucs (vocal separation tool) +$ pip install -U demucs + +# To exit the virtual environment +$ deactivate ``` -Or, an other way to do it: +# Use +To extract .wav audio from all MKVs in a folder : ```bash -$ mkvirtualenv keras_tf -p python3 # create the virtual envireonment, do it once -$ workon keras_tf # use the virtual envireonement - -# Here goes the install commands -$ pip install --upgrade tensorflow -$ pip install numpy scipy -$ pip install scikit-learn -$ pip install pillow -$ pip install h5py -$ pip install keras - -# don't know how to quit, find it yourself +$ ./extractWav.sh source_folder output_folder ``` -Or easier, install them directly without virtual environment. +To separate vocals from instruments in an audio file : +```bash +demucs --two-stems=vocal -o output_folder audio_file.wav +``` + +