diffwave

diffwave copied to clipboard

Unconditional synthesis

5

I"m running the this command to generate unconditional samples. `python -m diffwave.inference --fast /path/to/model -o output.wav` I've trained for almost 4k epochs on 7k+ sounds. I seem to get the...

berkeleymalagon

Code for evaluation in paper

6

I found some automatic evaluation metrics mentioned in the paper, where can I find these scripts so that I can reproduce the result and compare with others method. 

v-nhandt21

CUDA Error when loading checkpoint on more than one GPU

2

Hello. I am having an issue when using your code. If I try to resume a training from a checkpoint when having more than one GPU (I am using docker...

agonzalezd

xcmyz

Hi, I wander why using subset of Speech Command to train but not the whole dataset? In my experiments, diffusion model cannot handle dataset of a large data scale (1M...

ludanruan

This can be used for voice conversion right?

1

As in, train the vocoder just on one speaker, and when you inference, even with another speaker, it will sound like the one you trained on?

dillfrescott

Question about fientune the diffwave

1

Heya creator, thanks for your amazing contribution to implement diffwave model. I have a general question about the fientune the diffwave. If I use only one prompt voice to fine-tune...

ggbangyes

Question in the inference

3

the required spectrogram form is like [N,C,W]. spectrogram = # get your hands on a spectrogram in [N,C,W] format could you please explain these three dimensions? I use the code...

ggbangyes

I'm trying to run inference using a pretrained diffwave model on the output of a SepFormer model (separating a 2 speaker mixture). Creating the mel spectrogram and calling predict ```...

eitzo

preprocess problem

2

concurrent.futures.process.BrokenProcessPool: A process in the process pool was terminated abruptly while the future was running or pending.

yyh565655555