freeIsa

> Right now, the only way I found is to use the `showinfo` filter and parse the output string (as shown [here](https://github.com/kkroening/ffmpeg-python/issues/258#issuecomment-663378933_)). I could not find any other way than...

Hi, I am also trying to use BERT on data containing emojis but they are always encoded as from the Tokenizer. Has there been any progress in making emojis correctly...

@yezhengli-Mr9 I can share with you the notes I wrote down when experimenting with this (it's mainly copy&paste of instructions I found in the repository itself). Perhaps these can help...

> Hmmm. I am not sure about that. The new VL-pretrainining paper [OSCAR](https://arxiv.org/pdf/2004.06165.pdf) shows a strong score on img cap (CIDEr = 140) that you might be interested in. Thanks...