This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.
In the text mode, I know what the "character" stand for, but what dose "subword" stand for?
And what is the different between "subword.model", "subword-16k.model" and "subword-460.model"?
Hi,
In the text mode, I know what the "character" stand for, but what dose "subword" stand for? And what is the different between "subword.model", "subword-16k.model" and "subword-460.model"?
Thank you for your help