ddsp_pytorch

ddsp_pytorch copied to clipboard

```Traceback (most recent call last): File "train.py", line 69, in epochs = int(np.ceil(args.STEPS / len(dataloader))) ZeroDivisionError: division by zero``` my config.yaml ```data: data_location: ./data/ extension: "wav" preprocess: sampling_rate: &samplingrate 16000...

cliffordmanasseh

Hey there, currently the readme.md suggests the following command to train a model: ```python train.py --name mytraining --steps 10000000 --batch 16 --lr .001``` however the option `--lr .001` throws the...

iorhythm

Here is a version of `extract_loudness` that is almost a 1:1 copy of the fixed version of the magenta/ddsp `compute_loudness`. The changes are mostly: - take mean in amplitude scale,...

nielsrolf

Loudness is computed in a wrong way

2

Hello, Some time ago, I noticed [a bug in `compute_loudness` in magenta/ddsp](https://github.com/magenta/ddsp/issues/361), and I think this repo has a similar issue. Below is the loudness curve extracted for a sine...

nielsrolf

i'm trying to install the realtime Pd external on a linux machine which does have a cuda gpu, but i would like to experiment with inference on cpu. i'm doing:...

ahihi

Monitoring validation loss

1

Hi there, Thanks for the implementation. It's really well written! May I ask whether there's a need to add a validation function to monitor the validation loss as well? Seems...

guozixunnicolas

The external still need to be compiled and tested on windows.

caillonantoine

Start working on a max / msp external

caillonantoine

First of all, thanks a lot for providing this code, looks super helpful! Since I wanted to mess around with the code a bit, I was wondering if it is...

bluenote10

I was trying to run the preprocessing, but it failed with a Tensorflow error at the step when its trying to apply crepe. The error is somewhat cryptic (`INTERNAL: Failed...

bluenote10