HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
deepgram
kur
Python2017–2017
deepgram / kur

kur

Descriptive Deep Learning

2Distinct people
2Mentions
0Explicit recommenders
824GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Descriptive Deep Learning

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 2:17:07 AM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by hour2 dated mentions

Observed mentions: 2017-01-18 09:27:12 UTC to 2017-01-18 22:50:48 UTC.

012017-01-18 09:00:00 UTC to 2017-01-18 10:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJan 18, 09:002017-01-18 10:00:00 UTC to 2017-01-18 11:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 11:00:00 UTC to 2017-01-18 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 12:00:00 UTC to 2017-01-18 13:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 13:00:00 UTC to 2017-01-18 14:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 14:00:00 UTC to 2017-01-18 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 15:00:00 UTC to 2017-01-18 16:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsJan 18, 15:002017-01-18 16:00:00 UTC to 2017-01-18 17:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 17:00:00 UTC to 2017-01-18 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 18:00:00 UTC to 2017-01-18 19:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 19:00:00 UTC to 2017-01-18 20:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 20:00:00 UTC to 2017-01-18 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 21:00:00 UTC to 2017-01-18 22:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2017-01-18 22:00:00 UTC to 2017-01-18 23:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJan 18, 22:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Jan 18, 09:002017-01-18 09:00:00 UTC2017-01-18 10:00:00 UTC101
Jan 18, 10:002017-01-18 10:00:00 UTC2017-01-18 11:00:00 UTC000
Jan 18, 11:002017-01-18 11:00:00 UTC2017-01-18 12:00:00 UTC000
Jan 18, 12:002017-01-18 12:00:00 UTC2017-01-18 13:00:00 UTC000
Jan 18, 13:002017-01-18 13:00:00 UTC2017-01-18 14:00:00 UTC000
Jan 18, 14:002017-01-18 14:00:00 UTC2017-01-18 15:00:00 UTC000
Jan 18, 15:002017-01-18 15:00:00 UTC2017-01-18 16:00:00 UTC000
Jan 18, 16:002017-01-18 16:00:00 UTC2017-01-18 17:00:00 UTC000
Jan 18, 17:002017-01-18 17:00:00 UTC2017-01-18 18:00:00 UTC000
Jan 18, 18:002017-01-18 18:00:00 UTC2017-01-18 19:00:00 UTC000
Jan 18, 19:002017-01-18 19:00:00 UTC2017-01-18 20:00:00 UTC000
Jan 18, 20:002017-01-18 20:00:00 UTC2017-01-18 21:00:00 UTC000
Jan 18, 21:002017-01-18 21:00:00 UTC2017-01-18 22:00:00 UTC000
Jan 18, 22:002017-01-18 22:00:00 UTC2017-01-18 23:00:00 UTC101

What Hacker News says

1 sources
Deepgram is open sourcing Kur (http://kur.deepgram.com)! Kur is the worlds first descriptive Deep Learning software. Think of a model, describe it in a simple YAML or JSON file, and train to get state-of-the-art results. There's no need to code. Why we built Kur: Prototyping DNNs is a slow process. Most people doing deep learning want to iterate and try out different model architectures and learn from others. It's hard to do this using barebones backends like TensorFlow/Theano or even the higher abstraction of software like Keras. Kur is not speech specific. It can be used for images (we supply two examples), speech (we supply one example and DG is open sourcing a new audio dataset with it, the DEEPGRAM10), text, etc. There are CNN layers, RNN, dense, dropout, batch norm, etc. to pick and choose from. The best part? Kur does all the plumb
Read the rest
ing! You want one input but two outputs? Not a problem, describe that model in Kur! We're really pumped to be releasing Kur and would love to answer questions if you've got em. Thanks! Deepgram AI Research Team http://kur.deepgram.com http://github.com/deepgram/kur http://kurhub.com
In Show HN: Kur by Deepgram (YC S16) – Deep Learning Made Easy

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.