-
This project is web site that provide Converting text to soundFX service
-
We use ML Model based on riffusion fine tuned by serveral soundFXs
-
Pull all Repositorys down below
-
Run
-
Run riffusion Server
#Config Python Interpreter conda create --name riffusion python=3.9 conda activate riffusion #Install Dependency python -m pip install -r requirements.txt #If use other audio format rather than wav sudo apt-get install ffmpeg # linux brew install ffmpeg # mac conda install -c conda-forge ffmpeg # conda #Install CUDA or MPS(Mac OS) import torch torch.cuda.is_available() import torch torch.backends.mps.is_available() #Run Server python -m riffusion.server --host 127.0.0.1 --port 3013
-
Run ModelServer
python -m flask run
-
Run React front
npm install npm start
- https://github.com/jha2ee
- Train Riffusion Model
- https://github.com/xongjaemin
- Front-End
- https://github.com/destiny3912
- Back-End
-