search

neillu23 / CDiffuSE

Conditional Diffusion Probabilistic Model for Speech Enhancement
Apache License 2.0
215 stars 34 forks source link

Problems with execution #1

Open julius-richter opened 2 years ago

julius-richter commented 2 years ago

Dear authors,

thank you very much for uploading the code for CDiffuSE! Unfortunately I have some problems with the execution.

Would be great if you could address the following issues:

1.) In __main__.py there there is no --vocoder argument for pretraining the Diffwave model. Should I use --pretrain instead?

2.) In train.sh the argument --pretain does come with path of the pretrained model although it is a store_false argument. Should I use --pretrain_path for passing the model path?

3.) In params.py the inference noise schedule for the fast reverse sampling is different than the one described in the paper. Should it be inference_noise_schedule=[0.0001, 0.001, 0.01, 0.05, 0.2, 0.35]?

4.) In the predict function of inference.py the noisy signal y is not considered. This function seems to implement the sampling algorithm of DiffuSE. Could it be that you accidentally uploaded the inference.py of your old repo?

Thanks a lot in advance!

Best, Julius

neillu23 commented 2 years ago

Dear @julius-richter,

Thank you very much for pointing out the execution issues. Accidently I uploaded the old version of my code. I have updated all of the codes and added a README file for introducing the usage. I will also upload my pretrained models soon. Sorry for your inconvenience. Please tell me if you find any other issues with the code. Thank you again for your patience!

Best Regards, Yen-Ju