Jeff Tang

Just tested the script above with torch 1.9.0 and torchvision 0.10.0 installed on Mac and it works - what's your installed version of torch and torchvision and OS? Do they...

Did you create `d2go.pt` using the script in the repo, or use the model file directly in the repo?

Did you use PyTorch 1.9 and torchvision 0.10.0 to create your model? Then the build.gradle needs to be updated with 1.9.0 like [this](https://github.com/pytorch/android-demo-app/blob/master/ImageSegmentation/app/build.gradle) and use the lite version api like...

D2Go for PyTorch 1.9 works, but an updated script is required to create the model - please checkout the PyTorch 1.9 updated D2Go iOS demo app, steps 1-3 of [here](https://github.com/pytorch/ios-demo-app/tree/master/D2Go)...

Sorry for the late reply. Did you drag and drop the created model to the Xcode project?

Sorry for the late response. What's the error message?

Thanks and this has been fixed by using the latest 1.9.0.

You need to add `--text_list=sentences.txt` after `python synthesize.py`

> Hi @jeffxtang, it seems that we can run fft directly with pytorch from version 1.10, due to the PocketFFT support from this commit: [pytorch/pytorch@4036820](https://github.com/pytorch/pytorch/commit/4036820506693b71a96b9e20989bfe286acccd89) > > Can you confirm?...

> Hi, just following up if `torchaudio` is available on React Native now..? @mthrok @vincentqb @dkashkin Trying to do something like this: > > ``` > audio, sample_rate = librosa.load(audio_filepath,...