News for hackers. Stuff that matters.
Re:A speech-to-text practitioner’s criticisms of industry an... by totorovirus on Monday April 06, 2020 @12:15AM (#22790860)
Also, we have developed our internal framework that eases pretraining - finetuning to subtask pipeline. After months of usage it required a lot of refactoring to match the need of all forms of DNN models. I would like to hear from other ML engineers if they have a internal framework which generalizes at least one subfield of DNN(nlp, vision, speech etc)
Re:A speech-to-text practitioner’s criticisms of industry an... by snakers41 on Tuesday April 07, 2020 @02:06AM (#22800720)
Hi, my name is Alexander, I am an author of both Gradient pieces, Open STT and silero.ai

Interesting We did mostly the same Did you open source your data as well?

Re:A speech-to-text practitioner’s criticisms of industry an... by totorovirus on Sunday April 19, 2020 @11:49PM (#22920940)
I don't think my superiors are going to open our source code. Thanks for letting me know about your project