HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
Rayhane-mamah
Tacotron-2
Python2018–2019
Rayhane-mamah / Tacotron-2

Tacotron-2

DeepMind's Tacotron-2 Tensorflow implementation

3Distinct people
3Mentions
0Explicit recommenders
2.3KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

DeepMind's Tacotron-2 Tensorflow implementation

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

Mentioned in the same Hacker News threads. That is not proof they are substitutes.

This week on Hacker News

Nov 9–Nov 16 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/16/2026, 8:59:02 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 week3 dated mentions

Observed mentions: 2018-11-19 20:58:31 UTC to 2019-05-19 16:51:42 UTC. Weeks start Monday, UTC.

0122018-11-19 00:00:00 UTC to 2018-11-26 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsNov 192018-11-26 00:00:00 UTC to 2018-12-03 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-12-03 00:00:00 UTC to 2018-12-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-12-10 00:00:00 UTC to 2018-12-17 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-12-17 00:00:00 UTC to 2018-12-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-12-24 00:00:00 UTC to 2018-12-31 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2018-12-31 00:00:00 UTC to 2019-01-07 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-01-07 00:00:00 UTC to 2019-01-14 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-01-14 00:00:00 UTC to 2019-01-21 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-01-21 00:00:00 UTC to 2019-01-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-01-28 00:00:00 UTC to 2019-02-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-02-04 00:00:00 UTC to 2019-02-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-02-11 00:00:00 UTC to 2019-02-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsFeb 112019-02-18 00:00:00 UTC to 2019-02-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-02-25 00:00:00 UTC to 2019-03-04 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-03-04 00:00:00 UTC to 2019-03-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-03-11 00:00:00 UTC to 2019-03-18 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-03-18 00:00:00 UTC to 2019-03-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-03-25 00:00:00 UTC to 2019-04-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-04-01 00:00:00 UTC to 2019-04-08 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-04-08 00:00:00 UTC to 2019-04-15 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-04-15 00:00:00 UTC to 2019-04-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-04-22 00:00:00 UTC to 2019-04-29 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-04-29 00:00:00 UTC to 2019-05-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-05-06 00:00:00 UTC to 2019-05-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2019-05-13 00:00:00 UTC to 2019-05-20 00:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 commentsMay 13

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
Nov 192018-11-19 00:00:00 UTC2018-11-26 00:00:00 UTC101
Nov 262018-11-26 00:00:00 UTC2018-12-03 00:00:00 UTC000
Dec 32018-12-03 00:00:00 UTC2018-12-10 00:00:00 UTC000
Dec 102018-12-10 00:00:00 UTC2018-12-17 00:00:00 UTC000
Dec 172018-12-17 00:00:00 UTC2018-12-24 00:00:00 UTC000
Dec 242018-12-24 00:00:00 UTC2018-12-31 00:00:00 UTC000
Dec 312018-12-31 00:00:00 UTC2019-01-07 00:00:00 UTC000
Jan 72019-01-07 00:00:00 UTC2019-01-14 00:00:00 UTC000
Jan 142019-01-14 00:00:00 UTC2019-01-21 00:00:00 UTC000
Jan 212019-01-21 00:00:00 UTC2019-01-28 00:00:00 UTC000
Jan 282019-01-28 00:00:00 UTC2019-02-04 00:00:00 UTC000
Feb 42019-02-04 00:00:00 UTC2019-02-11 00:00:00 UTC000
Feb 112019-02-11 00:00:00 UTC2019-02-18 00:00:00 UTC000
Feb 182019-02-18 00:00:00 UTC2019-02-25 00:00:00 UTC000
Feb 252019-02-25 00:00:00 UTC2019-03-04 00:00:00 UTC000
Mar 42019-03-04 00:00:00 UTC2019-03-11 00:00:00 UTC000
Mar 112019-03-11 00:00:00 UTC2019-03-18 00:00:00 UTC000
Mar 182019-03-18 00:00:00 UTC2019-03-25 00:00:00 UTC000
Mar 252019-03-25 00:00:00 UTC2019-04-01 00:00:00 UTC000
Apr 12019-04-01 00:00:00 UTC2019-04-08 00:00:00 UTC000
Apr 82019-04-08 00:00:00 UTC2019-04-15 00:00:00 UTC000
Apr 152019-04-15 00:00:00 UTC2019-04-22 00:00:00 UTC000
Apr 222019-04-22 00:00:00 UTC2019-04-29 00:00:00 UTC000
Apr 292019-04-29 00:00:00 UTC2019-05-06 00:00:00 UTC000
May 62019-05-06 00:00:00 UTC2019-05-13 00:00:00 UTC000
May 132019-05-13 00:00:00 UTC2019-05-20 00:00:00 UTC202

What Hacker News says

1 sources
Worth noting that a big chunk of the core TTS code here is built on tools from other researchers like Ryuichi Yamamoto and Keith Ito, and they have great implementations to check out as well. The best quality I have heard in OSS is probably [1] from Ryuichi using the Tacotron 2 implementation of Rayhane Mamah, which is loosely what NVidia based some of their baseline code on recently as well [3][4]. There's also a colab notebook for this stuff, so you can try it directly without any pain https://colab.research.google.com/github/r9y9/Colaboratory/b... I also have my own pipeline for this (using some utilities from the above authors + a lot of my own hacks), for a forthcoming paper release here https://github.com/kastnerkyle/representation_mixing/tree/ma... , see the minimal demo. It has pretty fast sampling, but the audio quality is not a
Read the rest
s high as WaveNet. I'd really like to tie in with WaveGlow, but it's work in progress for me so far. NOTE: None of these have voice adaptivity per se, but given a model which trains well already + a multispeaker dataset with IDs such as VCTK, a lot of things become possible as getting a baseline model and data pipeline for TTS is quite difficult. [0] https://github.com/keithito/tacotron [1] https://r9y9.github.io/blog/2018/05/20/tacotron2/ [2] https://github.com/Rayhane-mamah/Tacotron-2 [3] https://github.com/NVIDIA/waveglow [4] https://github.com/NVIDIA/tacotron2
In Varying Speaking Styles with Neural Text-to-Speech

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.