Approximetal

I got OOM error, how can I deel with it? BTY, how can I load multiple data in one container？ `gadgetGPU = SpeedTorch.DataGadget(target_mel) gadgetGPU.gadgetInit() Traceback (most recent call last): File...

import cupy import SpeedTorch gadgetGPU = SpeedTorch.DataGadget('mel-20170001P00084I0004.npy') gadgetGPU.gadgetInit() [mel-20170001P00084I0004.zip](https://github.com/Santosh-Gupta/SpeedTorch/files/4024469/mel-20170001P00084I0004.zip) It seems `gadgetGPU.gadgetInit()`will result this error no matter which data I load.

> It looks like the data format is incorrect. It looks like there's an issue with how you're saving the data, and/or how your zipping the file. > > Checkout...

> Yup, I forgot the exact commands, but you can access your embedding data and mount them to CPU, in numpy form. It looks something like this YourModel.YourEmbeddingVariable.Weight.data.cpu().numpy() > >...

Thank you for replying! I can load files by using speedtorch now. But cupy doesn't support multi-thread, so I have to modify the thread from 8 to 1, after that,...

> > Thank you for replying! I can load files by using speedtorch now. But cupy doesn't support multi-thread, so I have to modify the thread from 8 to 1,...

> How many cores does that CPU have? I can't seem to look it up. > > I'm not too familiar with that model. But with a colab notebook perhaps...

Hi,@bshall @tunnermann I met the same problem, when I use different parameters to extract mel spectrogram and retrain the model, but the loss stop arround 2.9 and the result has...

> Hi @Approximetal, > > Quick question: are those samples from out-of-domain speakers or were those speakers in the training data? They are in the training dataset.

I use four dataset training together, including [VCTK-Corpus](https://homepages.inf.ed.ac.uk/jyamagis/page3/page58/page58.html), [VCC2020](http://www.vc-challenge.org/rules.html), a Chinese Dataset about 24h and a multi-lingual audiobook dataset about 150h. By the way, how to fine-tune the pre-train model?...