Jiahao Zhao

@abisee Thanks! When train model set `tf.app.flags.DEFINE_boolean('pointer_gen', True, 'If True, use pointer-generator model. If False, use baseline model.')` If it possible that decoding (beam search) generated summary have `[UNK]` token...

@abisee Thanks so much ! In the [paper](https://arxiv.org/abs/1704.04368), from both Supplementary Material and Figure 1, it seems pointer-generator model solved OOV problem. 1. Have you ever observed `[UNK]` token when...

By the way. I think SCPN and GAN also have some bugs. The example generated using these methods could not maintain semantic consistent with original input text at all.

The module that paraphrase-based attack needed is quite different from the module that TextAttack currently provided. I'm not sure how to merge paraphrase-based attack into TextAttack. 😅That's a hard task...

I find a phonetic notation called International Phonetic Alphabet(IPA) which support 100+ language for grapheme-to-phoneme. Maybe we can use IPA as the phoneme set for multilingual VC? I'll try it...

No. I'll not dive into this building way. I just try any-to-many example with provided checkpoints on my custom English source wav. The female voice of high-frequency part is omitted...

@MoonInTheRiver when will we see the midi data of POPCS?

To build a new image, more specifically: ``` FROM RUN rm -rf /usr/lib/x86_64-linux-gnu/libnvidia* /usr/lib/x86_64-linux-gnu/libcuda* ``` Then run `docker run -it --gpus all [the new image:tag] command`, it uses GPU successfully.

Any updates here?

Hi, @MoritzLaurer. It's been a long time since you propose this issue, and these headers haven't been released. Do you find some alternative way? Is there some other pre-trained discriminator...