Menu
▾
▴
kaldi-developers — Kaldi Developers
You can subscribe to this list here.
| 2011 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
(4) |
Jul
|
Aug
|
Sep
(1) |
Oct
(4) |
Nov
(1) |
Dec
(14) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2012 |
Jan
(1) |
Feb
(8) |
Mar
|
Apr
(1) |
May
(3) |
Jun
(13) |
Jul
(7) |
Aug
(11) |
Sep
(6) |
Oct
(14) |
Nov
(16) |
Dec
(1) |
| 2013 |
Jan
(3) |
Feb
(8) |
Mar
(17) |
Apr
(21) |
May
(27) |
Jun
(11) |
Jul
(11) |
Aug
(21) |
Sep
(39) |
Oct
(17) |
Nov
(39) |
Dec
(28) |
| 2014 |
Jan
(36) |
Feb
(30) |
Mar
(35) |
Apr
(17) |
May
(22) |
Jun
(28) |
Jul
(23) |
Aug
(41) |
Sep
(17) |
Oct
(10) |
Nov
(22) |
Dec
(56) |
| 2015 |
Jan
(30) |
Feb
(32) |
Mar
(37) |
Apr
(28) |
May
(79) |
Jun
(18) |
Jul
(35) |
Aug
|
Sep
(1) |
Oct
|
Nov
|
Dec
|
|
From: <jen...@a2...> - 2014-08-15 04:59:43
|
Kaldi - Build # 676 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-15 04:49:48
|
Kaldi - Build # 675 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-15 04:19:45
|
Kaldi - Build # 673 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-15 03:51:57
|
Kaldi - Build # 674 - Still Failing: See the build log in attachment for the details. |
|
From: Daniel P. <dp...@gm...> - 2014-08-14 18:32:23
|
Christopher, the previous failures were due to a problem with the code, but now it seems to be failing in this way: + cd .. + cd src + make clean Makefile:29: kaldi.mk: No such file or directory kaldi.mk does not exist; you have to run ./configure It seems to me like it's a problem with how it's being built: it's trying to do make clean before configure. Dan On Thu, Aug 14, 2014 at 2:02 PM, <jen...@a2...> wrote: > Kaldi - Build # 671 - Still Failing: > > See the build log in attachment for the details. > > > > ------------------------------------------------------------------------------ > > _______________________________________________ > Kaldi-developers mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-developers > > |
|
From: <jen...@a2...> - 2014-08-14 18:09:49
|
Kaldi - Build # 671 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-14 17:05:54
|
Kaldi - Build # 670 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-14 14:49:57
|
Kaldi - Build # 669 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-14 13:41:15
|
Kaldi - Build # 668 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-14 04:44:46
|
Kaldi - Build # 666 - Still Failing: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-13 07:29:45
|
Kaldi - Build # 661 - Fixed: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-08-13 01:40:09
|
Kaldi - Build # 660 - Still Failing: See the build log in attachment for the details. |
|
From: Steve G. <she...@ho...> - 2014-08-09 20:43:45
|
Dear Sir, I am a university lecturer from northeastern Thailand and I am also part of a charitable foundation called Udon Education Foundation (UEF). We have been involved in educational projects in this area for about seven years and are currently working on speech recognition software as part of an ongoing project to help primary school children in the region learn English. Would it be possible to speak to someone involved with The Apache Software Foundation or KALDI as we are looking at replacing purchased software with something 'home-grown'? We are working on speech synthesis, speech recognition and a student teacher reporting process and believe that KALDI could be ideal in the next stage of development. I would appreciate it if you could contact me with a view to starting some kind of dialogue to hopefully get the ball rolling. Many thanks, Steven Graham Khon Kaen University International College (KKUIC) KKUIC Email: st...@kk... KKUIC Web: http://home.kku.ac.th/steven Personal Email: st...@st... Personal Web: www.steves-english-zone.com Personal Skype: shed_chelsea |
|
From: <jen...@a2...> - 2014-08-08 06:44:28
|
Kaldi - Build # 651 - Failure: See the build log in attachment for the details. |
|
From: Daniel P. <dp...@gm...> - 2014-08-04 05:06:03
|
Can anyone help me finish the program nnet2bin/nnet1-to-raw-nnet.cc? To someone with Kaldi coding experience it shouldn't be too hard, as I've sketched it out already. Dan |
|
From: Korbinian R. <kor...@gm...> - 2014-07-30 11:41:38
|
Yes, that's possible. Indeed, if you follow the timit (or any other) recipe, you will only have to convert the regular alignments to phone alignments using ali-to-phones, and convert frame durations to time duration. You can also check phones-to-prons and related tools to get both phone and word time alignment. Korbinian. On Mon, Jul 28, 2014 at 9:31 AM, Rademan, CF, Mnr <156...@su...> < 156...@su...> wrote: > To whom it may concern, > > I would like to use Kaldi to transcribe speech into text. But I would > like to include additional information, that being the time stamped > phonemes pronounced in each spoken word. I am unaware of the readers > knowledge of the TIMIT database, but I would like to create a similar, but > much smaller version, of such a data set. The TIMIT database has recordings > of speech which include text files with timing information on phonetic > pronunciation during speech. Is it possible to create a similar output > using Kaldi? > > Kind regards, > Christo Rademan > > > ------------------------------------------------------------------------------ > Infragistics Professional > Build stunning WinForms apps today! > Reboot your WinForms applications with our WinForms controls. > Build a bridge from your legacy apps to the future. > > http://pubads.g.doubleclick.net/gampad/clk?id=153845071&iu=/4140/ostg.clktrk > _______________________________________________ > Kaldi-developers mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-developers > > |
|
From: Rademan, C. M. <156...@su...> - 2014-07-28 07:31:37
|
To whom it may concern, I would like to use Kaldi to transcribe speech into text. But I would like to include additional information, that being the time stamped phonemes pronounced in each spoken word. I am unaware of the readers knowledge of the TIMIT database, but I would like to create a similar, but much smaller version, of such a data set. The TIMIT database has recordings of speech which include text files with timing information on phonetic pronunciation during speech. Is it possible to create a similar output using Kaldi? Kind regards, Christo Rademan |
|
From: Daniel P. <dp...@gm...> - 2014-07-23 00:32:32
|
You can subscribe to this list at https://lists.sourceforge.net/lists/listinfo/kaldi-developers Dan On Tue, Jul 22, 2014 at 5:15 PM, Kim young joon <you...@sk...> wrote: > 보낸 사람: kal...@li... [ > kal...@li...] > 보낸 날짜: 2014년 7월 23일 수요일 오전 3:38 > 받는 사람: kal...@li... > 제목: Kaldi-developers Digest, Vol 27, Issue 11 > > Send Kaldi-developers mailing list submissions to > kal...@li... > > To subscribe or unsubscribe via the World Wide Web, visit > https://lists.sourceforge.net/lists/listinfo/kaldi-developers > or, via email, send a message with subject or body 'help' to > kal...@li... > > You can reach the person managing the list at > kal...@li... > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of Kaldi-developers digest..." > > > Today's Topics: > > 1. [Jenkins] Kaldi automatic build and test > (jen...@a2...) > > > ---------------------------------------------------------------------- > > Message: 1 > Date: Tue, 22 Jul 2014 20:01:09 +0200 (CEST) > From: jen...@a2... > Subject: [Kaldi-developers] [Jenkins] Kaldi automatic build and test > To: kal...@li..., ck...@a2... > Message-ID: > <105...@ks...> > Content-Type: text/plain; charset="utf-8" > > Kaldi - Build # 619 - Failure: > > See the build log in attachment for the details. > > -------------- next part -------------- > A non-text attachment was scrubbed... > Name: build.log > Type: application/octet-stream > Size: 40698 bytes > Desc: not available > > ------------------------------ > > > ------------------------------------------------------------------------------ > Want fast and easy access to all the code in your enterprise? Index and > search up to 200,000 lines of code with a free copy of Black Duck > Code Sight - the same software that powers the world's largest code > search on Ohloh, the Black Duck Open Hub! Try it now. > http://p.sf.net/sfu/bds > > ------------------------------ > > _______________________________________________ > Kaldi-developers mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-developers > > > End of Kaldi-developers Digest, Vol 27, Issue 11 > ************************************************ > > ------------------------------------------------------------------------------ > Want fast and easy access to all the code in your enterprise? Index and > search up to 200,000 lines of code with a free copy of Black Duck > Code Sight - the same software that powers the world's largest code > search on Ohloh, the Black Duck Open Hub! Try it now. > http://p.sf.net/sfu/bds > _______________________________________________ > Kaldi-developers mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-developers > |
|
From: Kim y. j. <you...@sk...> - 2014-07-23 00:30:57
|
보낸 사람: kal...@li... [kal...@li...]
보낸 날짜: 2014년 7월 23일 수요일 오전 3:38
받는 사람: kal...@li...
제목: Kaldi-developers Digest, Vol 27, Issue 11
Send Kaldi-developers mailing list submissions to
kal...@li...
To subscribe or unsubscribe via the World Wide Web, visit
https://lists.sourceforge.net/lists/listinfo/kaldi-developers
or, via email, send a message with subject or body 'help' to
kal...@li...
You can reach the person managing the list at
kal...@li...
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Kaldi-developers digest..."
Today's Topics:
1. [Jenkins] Kaldi automatic build and test
(jen...@a2...)
----------------------------------------------------------------------
Message: 1
Date: Tue, 22 Jul 2014 20:01:09 +0200 (CEST)
From: jen...@a2...
Subject: [Kaldi-developers] [Jenkins] Kaldi automatic build and test
To: kal...@li..., ck...@a2...
Message-ID:
<105...@ks...>
Content-Type: text/plain; charset="utf-8"
Kaldi - Build # 619 - Failure:
See the build log in attachment for the details.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: build.log
Type: application/octet-stream
Size: 40698 bytes
Desc: not available
------------------------------
------------------------------------------------------------------------------
Want fast and easy access to all the code in your enterprise? Index and
search up to 200,000 lines of code with a free copy of Black Duck
Code Sight - the same software that powers the world's largest code
search on Ohloh, the Black Duck Open Hub! Try it now.
http://p.sf.net/sfu/bds
------------------------------
_______________________________________________
Kaldi-developers mailing list
Kal...@li...
https://lists.sourceforge.net/lists/listinfo/kaldi-developers
End of Kaldi-developers Digest, Vol 27, Issue 11
************************************************ |
|
From: <jen...@a2...> - 2014-07-22 18:38:07
|
Kaldi - Build # 619 - Failure: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-07-21 20:38:22
|
Kaldi - Build # 616 - Fixed: See the build log in attachment for the details. |
|
From: <jen...@a2...> - 2014-07-21 19:09:09
|
Kaldi - Build # 615 - Failure: See the build log in attachment for the details. |
|
From: Korbinian R. <kor...@gm...> - 2014-07-21 19:01:21
|
Hi Saman, the probably easiest way to do so is to have a regular lexicon and grammar, i.e. you generate a new L.fst based on the actual words, a regular G.fst based on your ngrams/grammar, and then use mkgraph.sh to compose the final decoding graph. (I'm not sure if there is already a public script to change the lexicon, but you can infer the fundamentals from prepare_lang.sh). Korbinian. On Mon, Jul 21, 2014 at 3:17 PM, Saman Mousazadeh <smo...@gm...> wrote: > Hi, > I am using kaldi to produce a closed vocabulary speech recognition system. > How can I decode my FST using a pre-trained model (HCL) whose output is > phone and a G FST which is a lexicon (note that G now is an FST not an > acceotor. To be more clear in training step, I have used a large data base > while the lexicon (L) was an identity mapping (i.e. eg. AH1 AH1). Now in > testing stage, I want to use G built from a limited lexicon. Hence G is now > an FST not an acceptor. The decode.sh works but it seems that it does not > use G at all. > hope to hear from you a.s.a.p > Best regards and thanks in advance > Saman > > > > ------------------------------------------------------------------------------ > Want fast and easy access to all the code in your enterprise? Index and > search up to 200,000 lines of code with a free copy of Black Duck > Code Sight - the same software that powers the world's largest code > search on Ohloh, the Black Duck Open Hub! Try it now. > http://p.sf.net/sfu/bds > _______________________________________________ > Kaldi-developers mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-developers > |
|
From: Daniel P. <dp...@gm...> - 2014-07-21 17:46:59
|
Can someone else please respond to this? I don't have time right now. Dan On Mon, Jul 21, 2014 at 6:17 AM, Saman Mousazadeh <smo...@gm...> wrote: > Hi, > I am using kaldi to produce a closed vocabulary speech recognition system. > How can I decode my FST using a pre-trained model (HCL) whose output is > phone and a G FST which is a lexicon (note that G now is an FST not an > acceotor. To be more clear in training step, I have used a large data base > while the lexicon (L) was an identity mapping (i.e. eg. AH1 AH1). Now in > testing stage, I want to use G built from a limited lexicon. Hence G is now > an FST not an acceptor. The decode.sh works but it seems that it does not > use G at all. > hope to hear from you a.s.a.p > Best regards and thanks in advance > Saman > > > |
|
From: Saman M. <smo...@gm...> - 2014-07-21 13:17:40
|
Hi, I am using kaldi to produce a closed vocabulary speech recognition system. How can I decode my FST using a pre-trained model (HCL) whose output is phone and a G FST which is a lexicon (note that G now is an FST not an acceotor. To be more clear in training step, I have used a large data base while the lexicon (L) was an identity mapping (i.e. eg. AH1 AH1). Now in testing stage, I want to use G built from a limited lexicon. Hence G is now an FST not an acceptor. The decode.sh works but it seems that it does not use G at all. hope to hear from you a.s.a.p Best regards and thanks in advance Saman |
23 messages has been excluded from this view by a project administrator.
