⚠️⚠️⚠️⚠️⚠️ REPOSITORY TRANSFERED TO https://github.com/acids-ircam/ddsp_pytorch ⚠️⚠️⚠️⚠️⚠️
Implementation of the DDSP model using PyTorch. This implementation can be exported to a torchscript model, ready to be used inside a realtime environment (see this video).
Edit the config.yaml
file to fit your needs (audio location, preprocess folder, sampling rate, model parameters…), then preprocess your data using
python preprocess.py
You can then train your model using
python train.py --name mytraining --epochs 10000000 --batch 16 --lr .001
Once trained, export it using
python export.py --run runs/mytraining/
It will produce a file named ddsp_pretrained_mytraining.ts
, that you can use inside a python environment like that
import torch
model = torch.jit.load("ddsp_pretrained_mytraining.ts")
pitch = torch.randn(1, 200, 1)
loudness = torch.randn(1, 200, 1)
audio = model(pitch, loudness)
If you want to use DDSP in realtime (yeah), we provide a pure data external wrapping the all thing. Simply pass the --realtime true
option when exporting. This will disable the reverb and enable the use of the model in realtime. For now the external works on CPU, but you can enable GPU accelerated inference by changing realtime/ddsp_tilde/ddsp_model.h
DEVICE
to torch::kCUDA
.
Inside Pd, simply send load your_model.ts
to the ddsp~
object. The first inlet must be a pitch signal, the second a loudness signal. It can be directly plugged to the sigmund~
object for real-time timbre transfer ;)
You will need cmake
, a C++ compiler, and libtorch
somewhere on your computer. Then, run
cd realtime
mkdir build
cd build
cmake ../ -DCMAKE_PREFIX_PATH=/path/to/libtorch -DCMAKE_BUILD_TYPE=Release
make
The Pd external still need some optimization, it will receive some updates very soon.