DiffSinger

DiffSinger copied to clipboard

AttributeError: 'HifiGAN' object has no attribute 'model'

5

I'm following the instructions to train a model for DiffSinger, but there seem to be some issues with vocoders/hifigan.py: "# first run fs2 infer;" ``` $ CUDA_VISIBLE_DEVICES=0 python tasks/run.py --config...

duheyu

Hello! Thank you for this great repo. I saw that there is a new midi version tutorial with the opencpop, but you also mentioned the vocoder need to be fine-tuned...

funkgeek

When I'm trying to run train task and use parameters in pre trained optimizer This error occurs in pl_utils.py at: # restore the optimizers optimizer_states = checkpoint['optimizer_states'] for optimizer, opt_state...

selyu504

Hi, Thank you for sharing the pre-trained model of HiFiGAN Singing! I would like to use only the vocoder part for another research, so I extracted the "hifigan.py" file and...

powei-C

想在移动设备上使用，请问能否增加java版本？

watersoft123

I find that there are some bad cases in F0 prediction.

7

I find that there are some bad cases in F0 prediction. I recommend people to increase 'predictor_layers' or decrease 'predictor_dropout' to enhance the ability of pitch predictor for the part...

newportchen

about 'An Easier Trick for Boundary Prediction'

5

In your paper, we can get the predicted boundary as follows:  then I implemented 'An Easier Trick for Boundary Prediction' in my repo following the trick: https://github.com/keonlee9420/DiffSinger/blob/f849f8def5abb38ad272a384e8bec838ea1957a4/boundary_predictor.py#L14-L45 and there...

keonlee9420

Looking forward for the midi data of POPCS~!

1

Looking forward for the midi data of POPCS~!

YawYoung

kevink2424

 I train diffsing with private dataset but i got some results not clear. Can you tell me the reason of this picture?

daxiangpanda