search

rizkiarm / LipNet

Keras implementation of 'LipNet: End-to-End Sentence-level Lipreading'
MIT License
628 stars 224 forks source link

about grid dataset #45

Closed crazygirl1992 closed 6 years ago

crazygirl1992 commented 6 years ago

hello,now i want run the code with my dataset,but i don't know the grid dataset's text 0 14000 sil 14000 19750 bin 19750 25000 blue 25000 30250 by 30250 38750 s 38750 49000 five 49000 61000 please 61000 74500 sil the data before the word means what,and how can i change my data to train the code?thank you @rizkiarm @michiyosony

michiyosony commented 6 years ago

The first number indicates the start of that word. The second number indicates the stop. I couldn't find a source for this, but it appears that they are frame numbers x 1000. So frames 0-14 are silence, frames 14-20 are the word "bin", etc.

rizkiarm commented 6 years ago

@michiyosony is correct. Please do visit their website for more details: http://spandh.dcs.shef.ac.uk/gridcorpus/