p0p

Hello, if you feel something is missing or would be helpful for the community, please contribute by issuing a PR. Thanks a lot!

Yes. That's correct.

@markriedl I think in the notebook. Fixed in #3 .

Check the device type of the tensors at the error line. Move them all to either GPU or cpu and run.

For precise analysis of the error, append the following code, you can see the tensors' respective devices. In the `TTS/TTS/tts/layers/losses.py` file, ``` #add immediately above L193 tensors_to_check = [x.masked_select(mask), target.masked_select(mask),...

> @BrukArkady The answer is given by @p0p4k. To be precise, you should change `line #3150` of `functional.py` from: > > ``` > return torch.binary_cross_entropy_with_logits(input, target, weight, pos_weight, reduction_enum) >...

> > > @BrukArkady The answer is given by @p0p4k. To be precise, you should change `line #3150` of `functional.py` from: > > > ``` > > > return torch.binary_cross_entropy_with_logits(input,...

That is just `numpy` warning you can ignore. To use GPU, add the following in the first cell of the notebook. ``` import os os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID" # see issue #152 os.environ["CUDA_VISIBLE_DEVICES"]="0"...

On side note, I have tested below config on python=3.10, pytorch=1.11, torchaudio=0.11.0 and works well with no errors. _Due to recent bump in numpy errors while installing TTS, I believe...

I will continue it after 2 weeks. Can I reopen it later on?