Derek Chia

> > @Kabur I referenced the method you mentioned above but I meet a new problem. > > FileNotFoundError: [Errno 2] No such file or directory: './libri_fbank80_subword5000/bpe/bpe.vocab' > > It...

> I added --model_type=bpe , but I still got the same error: > > FileNotFoundError: [Errno 2] No such file or directory: > './libri_fbank80_subword5000/bpe/bpe.vocab' Did you do take a look...

> Found this error. But it works now when I compiled the sentencepiece from source. Don't do a `pip install sentencepiece` and this should work or an error > >...

I got the same error as well, seems like there is an empty list some where

I got it to work by first converting the GRID video to frames using `scripts/extract_mouth_batch.py` and made the changes proposed by @acarlos in #37 . Feel free to email me...

@gzz666 I'm running Ubuntu, not Windows, so I cannot help you with the FFMPEG installation. Sorry.

@gzz666 Can you paste the entire error message here?

I was too able to train on frames (after running `scripts/extract_mouth_batch.py`). For those struggling to get this to work, please extract the lip/mouth into frames before training.

Maybe you can start with inferencing with the weights provided?

You will need to: 1. set up the environment by running `pip install -e .` in the folder, then 2. download the GRID dataset, and extract frames with lip actions...