Jason Wei

Same. I want to create manifests for some portable CLI tools written in Rust, like [tokei](https://github.com/XAMPPRocky/tokei/releases/) and [genact](https://github.com/svenstaro/genact/releases/). But `wingetcreate` failed to parse these packages.

错别字： 由于读书的时候试图**高**过游戏开发的关系 ↓ 由于读书的时候试图**搞**过游戏开发的关系

https://github.com/Rayhane-mamah/Tacotron-2/issues/29#issuecomment-465932878 > It's 'ground-truth-aligned'. Meaning the state of the network follows the ground truth, 'real' spectrogram's timing. Yielding a predicted spectrogram that is the same length of hops as the...

Mixture of logistic distributions.

You can use 仮名 or ローマ字 as symbols.

You need to modify `_characters` in `tacotron/utils/symbols.py` for non-English language. Then modify `build_from_path()` in `datasets/preprocessor.py` according to JSUT dataset's format. I haven't tried JSUT dataset, since I don't speak Japanese...

I am not sure about this, but I think you can put only hiraganas and katakanas in _characters, and replace kanjis in JSUT dataset's transcription file with hiraganas using some...

Use Tensorflow 1.10. I trained Wavenet on Tensorflow 1.14, and I got an error when I tried to do inference from checkpoint file. It seemed that some variables were missing...

> I can't do Wavenet inference with tensorflow 1.14. There's a bug with checkpoint loading. > Tensorflow 1.10 works fine for me. > > Good to know. Thanks. > (Does...

Commenting `self._track_checkpointable(layer, name='layer')` works fine for me (there are 2 lines). @menu23 I had this issue with tensorflow 1.14. I downgraded to tensorflow 1.10, retrained wavenet, and the error is...