News for hackers. Stuff that matters.

A comment on A speech-to-text practitioner’s criticisms of industry and academia. Parent comment

Re:A speech-to-text practitioner’s criticisms of industry an... by nmfisher on Monday April 06, 2020 @02:40AM (#22791375)
Are you talking about wav2letter@anywhere?

If so, I haven't dug deeply yet, but I suspect the author's point stands - inference-time efficiency is one thing, but training compute (and separately, data-efficiency) is another.

I don't think the author is necessarily criticizing anyone, and I don't think he/she is saying that these tools/models/papers/etc aren't welcome. My read is that "pushing STT beyond the FAANG use-case means we should stop confining ourselves to FAANG-scale data and models".

[ Parent | on HN ]
Re:A speech-to-text practitioner’s criticisms of industry an... by gok on Tuesday April 07, 2020 @12:45PM (#22804834)
Particularly https://github.com/facebookresearch/wav2letter/blob/master/r...

It uses a publicly available huge training set

[ Parent | on HN ]