Menu
▾
▴
kaldi-users — Kaldi Users
You can subscribe to this list here.
| 2011 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
(2) |
Aug
(2) |
Sep
(1) |
Oct
(1) |
Nov
|
Dec
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2012 |
Jan
|
Feb
|
Mar
(8) |
Apr
(4) |
May
(2) |
Jun
(1) |
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2013 |
Jan
|
Feb
(2) |
Mar
(2) |
Apr
(7) |
May
(31) |
Jun
(40) |
Jul
(65) |
Aug
(37) |
Sep
(12) |
Oct
(57) |
Nov
(15) |
Dec
(35) |
| 2014 |
Jan
(3) |
Feb
(30) |
Mar
(57) |
Apr
(26) |
May
(49) |
Jun
(26) |
Jul
(63) |
Aug
(33) |
Sep
(20) |
Oct
(153) |
Nov
(62) |
Dec
(20) |
| 2015 |
Jan
(6) |
Feb
(21) |
Mar
(42) |
Apr
(33) |
May
(76) |
Jun
(102) |
Jul
(39) |
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 16:26:34
|
Good to hear. I am trying from last week to learn how was it designed. When are you going to commit the changes? In days in weeks? I would like to use the new code to build upon. I would like to run some experiments first, than I need to build a python wrapper (my project requirements). Currently I am finishing a python wrapper for the compute-mfcc-featscc , gmm-latgen-faster.cc and lattice-best-path.cc using https://cffi.readthedocs.org/en/release-0.6/. Basically I am trying to build shared library containing functionality of the compute-mfcc-featscc , gmm-latgen-faster.cc and lattice-best-path.cc. Than the rest is very easy using python-cffi ( https://cffi.readthedocs.org/en/release-0.6/). I guess there is no plan to distribute Kaldi as shared library, right? (Pity for me) Ondra On 14 May 2013 18:13, Mailing list used for User Communication and Updates < kal...@li...> wrote: > By the way, since we are talking about the online decoder, I should > mention that I am just about to commit some changes, involving a > reorganization of the internal code and the addition of unit-tests. Vassil > has checked that it still works for his demo. > > Dan > > > > On Tue, May 14, 2013 at 12:09 PM, Daniel Povey <dp...@gm...> wrote: > >> You have to be careful that you give the online decoder the right options >> corresponding tot the features that you used. See if there are any >> non-default options in your MFCC extraction or PLP extraction, for >> instance, and that the LDA window is set correctly. >> >> Dan >> >> >> >> On Tue, May 14, 2013 at 10:10 AM, Mailing list used for User >> Communication and Updates <kal...@li...> wrote: >> >>> As I said on my data have results like 70% WER. It is due to some bug, >>> which I have not fixed yet. >>> >>> In the online demo I tried to use our test (quite general data - in >>> terms of LM) and test it against online demo, >>> because as far as I understood it the online demo was trained on the >>> same data which are in supplied as the test data. >>> >>> Basically, I was asking for the numbers because I need to know if I have >>> still bug in my script or it is just normal performance. >>> >>> Thansk >>> >>> Ondra >>> >>> >>> >>> >>> On 14 May 2013 15:39, Mailing list used for User Communication and >>> Updates <kal...@li...> wrote: >>> >>>> Hi, >>>> >>>> I don't have specific numbers to share (as I said the online decoder >>>> is not rigorously tested as far as I know). In principle I think the >>>> online decoder should perform slightly worse than the offline versions >>>> due to things like online CMN computation. >>>> >>>> What do you mean exactly when you say that the results for the online >>>> demo are not so good? As far as I remember the WER for the test WAV >>>> files was about 7%, which is not so bad as today's speech recognition >>>> goes. Of course the WER in this case is so low, because the language >>>> model is relatively small and perfectly matches the test files (the LM >>>> is trained on the text corresponding to the audio book from which the >>>> test utterances were taken - not the best practice of course). >>>> >>>> Vassil >>>> >>>> On Tue, May 14, 2013 at 2:59 PM, Mailing list used for User >>>> Communication and Updates <kal...@li...> wrote: >>>> > Hi Vassil, >>>> > >>>> > May I asked about the performance (in terms of WER/SER) of online >>>> decoder? >>>> > >>>> > What is the expected WER for online-wav-gmm-decode-faster, >>>> > if I reached with gmm-latgen-faster scores in table below? >>>> > I would like to use the same trained models for >>>> online-wav-gmm-decode-faster >>>> > as >>>> > I used for gmm-latgen-faster (and lattice-best-path). >>>> > >>>> > exp RT coef WER >>>> > _ri3b_fmmi_b 11.33336625 19.42 >>>> > tri2b_mpe 1.2307175 21.22 >>>> > mono 2.8952 49.88 >>>> > tri3b_mmi 1.24198625 20.01 >>>> > tri1 2.398165 28.13 >>>> > tri2b_mmi 1.65662125 20.34 >>>> > tri2a 2.15838 28.43 >>>> > tri2b 1.451105 27.96 >>>> > tri3b 1.0596075 27.79 >>>> > tri3b_fmmi_c 11.4361875 19.13 >>>> > tri2b_mmi_b0.05 2.0089575 19.64 >>>> > tri3b_fmmi_d 16.1227625 19.5 >>>> > >>>> > The names and the core settings of experiments are the same as in >>>> > egs/voxforge/s5/run.sh >>>> > >>>> > >>>> > With the online-wav-gmm-decode-faster >>>> > I reached really bad scores due to bugs (which I still need to fix), >>>> > but still also in the online demo the results are not so nice. >>>> > >>>> > Thanks for any help >>>> > >>>> > Ondra Platek >>>> > >>>> > >>>> > On 26 April 2013 15:35, Mailing list used for User Communication and >>>> Updates >>>> > <kal...@li...> wrote: >>>> >> >>>> >> Hi, >>>> >> as for taking input from a microphone you might want to have a look >>>> at >>>> >> the (optional) online decoder. There is a simple demo script in >>>> >> egs/voxforge/online-demo. There is also a version that can decode >>>> .wav >>>> >> files without a separate feature extraction step. The code is not >>>> >> extensively tested and lacks some polish and flexibility, but perhaps >>>> >> you can use it as an example. >>>> >> >>>> >> Vassil >>>> >> >>>> >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User >>>> >> Communication and Updates <kal...@li...> wrote: >>>> >> > Dear all, >>>> >> > I'm working on the development of an R&D voice-to-voice module and >>>> I >>>> >> > would >>>> >> > like to use Kaldi for the transcription part (we made some tests >>>> with >>>> >> > PocketSphinx but we found that Kaldi is more adapted for our task). >>>> >> > >>>> >> > The problem is that I'm not really expert in speech2text (Kaldi >>>> models >>>> >> > will >>>> >> > be provided by another team) and I did not found scripts (or >>>> plugins) >>>> >> > allowing an easy integration of Kaldi : How to manage streams (with >>>> >> > gstreammer for example)? how we can decode a single wav file? etc. >>>> >> > >>>> >> > Is someone else has already handle these problems? are there any >>>> scripts >>>> >> > to >>>> >> > facilitate this task? >>>> >> > >>>> >> > thanks in advance for your reply, >>>> >> > >>>> >> > Best regards >>>> >> > >>>> >> > >>>> >> > >>>> >> > >>>> ------------------------------------------------------------------------------ >>>> >> > Try New Relic Now & We'll Send You this Cool Shirt >>>> >> > New Relic is the only SaaS-based application performance monitoring >>>> >> > service >>>> >> > that delivers powerful full stack analytics. Optimize and monitor >>>> your >>>> >> > browser, app, & servers with just a few lines of code. Try New >>>> Relic >>>> >> > and get this awesome Nerd Life shirt! >>>> >> > http://p.sf.net/sfu/newrelic_d2d_apr >>>> >> > _______________________________________________ >>>> >> > Kaldi-users mailing list >>>> >> > Kal...@li... >>>> >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >>>> >> > >>>> >> >>>> >> >>>> >> >>>> ------------------------------------------------------------------------------ >>>> >> Try New Relic Now & We'll Send You this Cool Shirt >>>> >> New Relic is the only SaaS-based application performance monitoring >>>> >> service >>>> >> that delivers powerful full stack analytics. Optimize and monitor >>>> your >>>> >> browser, app, & servers with just a few lines of code. Try New Relic >>>> >> and get this awesome Nerd Life shirt! >>>> http://p.sf.net/sfu/newrelic_d2d_apr >>>> >> _______________________________________________ >>>> >> Kaldi-users mailing list >>>> >> Kal...@li... >>>> >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>>> > >>>> > >>>> > >>>> > >>>> ------------------------------------------------------------------------------ >>>> > AlienVault Unified Security Management (USM) platform delivers >>>> complete >>>> > security visibility with the essential security capabilities. Easily >>>> and >>>> > efficiently configure, manage, and operate all of your security >>>> controls >>>> > from a single console and one unified framework. Download a free >>>> trial. >>>> > http://p.sf.net/sfu/alienvault_d2d >>>> > _______________________________________________ >>>> > Kaldi-users mailing list >>>> > Kal...@li... >>>> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >>>> > >>>> >>>> >>>> ------------------------------------------------------------------------------ >>>> AlienVault Unified Security Management (USM) platform delivers complete >>>> security visibility with the essential security capabilities. Easily and >>>> efficiently configure, manage, and operate all of your security controls >>>> from a single console and one unified framework. Download a free trial. >>>> http://p.sf.net/sfu/alienvault_d2d >>>> _______________________________________________ >>>> Kaldi-users mailing list >>>> Kal...@li... >>>> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>>> >>> >>> >>> >>> ------------------------------------------------------------------------------ >>> AlienVault Unified Security Management (USM) platform delivers complete >>> security visibility with the essential security capabilities. Easily and >>> efficiently configure, manage, and operate all of your security controls >>> from a single console and one unified framework. Download a free trial. >>> http://p.sf.net/sfu/alienvault_d2d >>> _______________________________________________ >>> Kaldi-users mailing list >>> Kal...@li... >>> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> >>> >> > > > ------------------------------------------------------------------------------ > AlienVault Unified Security Management (USM) platform delivers complete > security visibility with the essential security capabilities. Easily and > efficiently configure, manage, and operate all of your security controls > from a single console and one unified framework. Download a free trial. > http://p.sf.net/sfu/alienvault_d2d > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 16:13:17
|
By the way, since we are talking about the online decoder, I should mention that I am just about to commit some changes, involving a reorganization of the internal code and the addition of unit-tests. Vassil has checked that it still works for his demo. Dan On Tue, May 14, 2013 at 12:09 PM, Daniel Povey <dp...@gm...> wrote: > You have to be careful that you give the online decoder the right options > corresponding tot the features that you used. See if there are any > non-default options in your MFCC extraction or PLP extraction, for > instance, and that the LDA window is set correctly. > > Dan > > > > On Tue, May 14, 2013 at 10:10 AM, Mailing list used for User Communication > and Updates <kal...@li...> wrote: > >> As I said on my data have results like 70% WER. It is due to some bug, >> which I have not fixed yet. >> >> In the online demo I tried to use our test (quite general data - in terms >> of LM) and test it against online demo, >> because as far as I understood it the online demo was trained on the same >> data which are in supplied as the test data. >> >> Basically, I was asking for the numbers because I need to know if I have >> still bug in my script or it is just normal performance. >> >> Thansk >> >> Ondra >> >> >> >> >> On 14 May 2013 15:39, Mailing list used for User Communication and >> Updates <kal...@li...> wrote: >> >>> Hi, >>> >>> I don't have specific numbers to share (as I said the online decoder >>> is not rigorously tested as far as I know). In principle I think the >>> online decoder should perform slightly worse than the offline versions >>> due to things like online CMN computation. >>> >>> What do you mean exactly when you say that the results for the online >>> demo are not so good? As far as I remember the WER for the test WAV >>> files was about 7%, which is not so bad as today's speech recognition >>> goes. Of course the WER in this case is so low, because the language >>> model is relatively small and perfectly matches the test files (the LM >>> is trained on the text corresponding to the audio book from which the >>> test utterances were taken - not the best practice of course). >>> >>> Vassil >>> >>> On Tue, May 14, 2013 at 2:59 PM, Mailing list used for User >>> Communication and Updates <kal...@li...> wrote: >>> > Hi Vassil, >>> > >>> > May I asked about the performance (in terms of WER/SER) of online >>> decoder? >>> > >>> > What is the expected WER for online-wav-gmm-decode-faster, >>> > if I reached with gmm-latgen-faster scores in table below? >>> > I would like to use the same trained models for >>> online-wav-gmm-decode-faster >>> > as >>> > I used for gmm-latgen-faster (and lattice-best-path). >>> > >>> > exp RT coef WER >>> > _ri3b_fmmi_b 11.33336625 19.42 >>> > tri2b_mpe 1.2307175 21.22 >>> > mono 2.8952 49.88 >>> > tri3b_mmi 1.24198625 20.01 >>> > tri1 2.398165 28.13 >>> > tri2b_mmi 1.65662125 20.34 >>> > tri2a 2.15838 28.43 >>> > tri2b 1.451105 27.96 >>> > tri3b 1.0596075 27.79 >>> > tri3b_fmmi_c 11.4361875 19.13 >>> > tri2b_mmi_b0.05 2.0089575 19.64 >>> > tri3b_fmmi_d 16.1227625 19.5 >>> > >>> > The names and the core settings of experiments are the same as in >>> > egs/voxforge/s5/run.sh >>> > >>> > >>> > With the online-wav-gmm-decode-faster >>> > I reached really bad scores due to bugs (which I still need to fix), >>> > but still also in the online demo the results are not so nice. >>> > >>> > Thanks for any help >>> > >>> > Ondra Platek >>> > >>> > >>> > On 26 April 2013 15:35, Mailing list used for User Communication and >>> Updates >>> > <kal...@li...> wrote: >>> >> >>> >> Hi, >>> >> as for taking input from a microphone you might want to have a look at >>> >> the (optional) online decoder. There is a simple demo script in >>> >> egs/voxforge/online-demo. There is also a version that can decode .wav >>> >> files without a separate feature extraction step. The code is not >>> >> extensively tested and lacks some polish and flexibility, but perhaps >>> >> you can use it as an example. >>> >> >>> >> Vassil >>> >> >>> >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User >>> >> Communication and Updates <kal...@li...> wrote: >>> >> > Dear all, >>> >> > I'm working on the development of an R&D voice-to-voice module and I >>> >> > would >>> >> > like to use Kaldi for the transcription part (we made some tests >>> with >>> >> > PocketSphinx but we found that Kaldi is more adapted for our task). >>> >> > >>> >> > The problem is that I'm not really expert in speech2text (Kaldi >>> models >>> >> > will >>> >> > be provided by another team) and I did not found scripts (or >>> plugins) >>> >> > allowing an easy integration of Kaldi : How to manage streams (with >>> >> > gstreammer for example)? how we can decode a single wav file? etc. >>> >> > >>> >> > Is someone else has already handle these problems? are there any >>> scripts >>> >> > to >>> >> > facilitate this task? >>> >> > >>> >> > thanks in advance for your reply, >>> >> > >>> >> > Best regards >>> >> > >>> >> > >>> >> > >>> >> > >>> ------------------------------------------------------------------------------ >>> >> > Try New Relic Now & We'll Send You this Cool Shirt >>> >> > New Relic is the only SaaS-based application performance monitoring >>> >> > service >>> >> > that delivers powerful full stack analytics. Optimize and monitor >>> your >>> >> > browser, app, & servers with just a few lines of code. Try New Relic >>> >> > and get this awesome Nerd Life shirt! >>> >> > http://p.sf.net/sfu/newrelic_d2d_apr >>> >> > _______________________________________________ >>> >> > Kaldi-users mailing list >>> >> > Kal...@li... >>> >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> >> > >>> >> >>> >> >>> >> >>> ------------------------------------------------------------------------------ >>> >> Try New Relic Now & We'll Send You this Cool Shirt >>> >> New Relic is the only SaaS-based application performance monitoring >>> >> service >>> >> that delivers powerful full stack analytics. Optimize and monitor your >>> >> browser, app, & servers with just a few lines of code. Try New Relic >>> >> and get this awesome Nerd Life shirt! >>> http://p.sf.net/sfu/newrelic_d2d_apr >>> >> _______________________________________________ >>> >> Kaldi-users mailing list >>> >> Kal...@li... >>> >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> > >>> > >>> > >>> > >>> ------------------------------------------------------------------------------ >>> > AlienVault Unified Security Management (USM) platform delivers complete >>> > security visibility with the essential security capabilities. Easily >>> and >>> > efficiently configure, manage, and operate all of your security >>> controls >>> > from a single console and one unified framework. Download a free trial. >>> > http://p.sf.net/sfu/alienvault_d2d >>> > _______________________________________________ >>> > Kaldi-users mailing list >>> > Kal...@li... >>> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> > >>> >>> >>> ------------------------------------------------------------------------------ >>> AlienVault Unified Security Management (USM) platform delivers complete >>> security visibility with the essential security capabilities. Easily and >>> efficiently configure, manage, and operate all of your security controls >>> from a single console and one unified framework. Download a free trial. >>> http://p.sf.net/sfu/alienvault_d2d >>> _______________________________________________ >>> Kaldi-users mailing list >>> Kal...@li... >>> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> >> >> >> >> ------------------------------------------------------------------------------ >> AlienVault Unified Security Management (USM) platform delivers complete >> security visibility with the essential security capabilities. Easily and >> efficiently configure, manage, and operate all of your security controls >> from a single console and one unified framework. Download a free trial. >> http://p.sf.net/sfu/alienvault_d2d >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> >> > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 16:13:02
|
Thanks! That would be it! I changed the MFCC features to be more HTK compatible (for comparing with HDecode). Ondra On 14 May 2013 18:09, Mailing list used for User Communication and Updates < kal...@li...> wrote: > You have to be careful that you give the online decoder the right options > corresponding tot the features that you used. See if there are any > non-default options in your MFCC extraction or PLP extraction, for > instance, and that the LDA window is set correctly. > > Dan > > > > On Tue, May 14, 2013 at 10:10 AM, Mailing list used for User Communication > and Updates <kal...@li...> wrote: > >> As I said on my data have results like 70% WER. It is due to some bug, >> which I have not fixed yet. >> >> In the online demo I tried to use our test (quite general data - in terms >> of LM) and test it against online demo, >> because as far as I understood it the online demo was trained on the same >> data which are in supplied as the test data. >> >> Basically, I was asking for the numbers because I need to know if I have >> still bug in my script or it is just normal performance. >> >> Thansk >> >> Ondra >> >> >> >> >> On 14 May 2013 15:39, Mailing list used for User Communication and >> Updates <kal...@li...> wrote: >> >>> Hi, >>> >>> I don't have specific numbers to share (as I said the online decoder >>> is not rigorously tested as far as I know). In principle I think the >>> online decoder should perform slightly worse than the offline versions >>> due to things like online CMN computation. >>> >>> What do you mean exactly when you say that the results for the online >>> demo are not so good? As far as I remember the WER for the test WAV >>> files was about 7%, which is not so bad as today's speech recognition >>> goes. Of course the WER in this case is so low, because the language >>> model is relatively small and perfectly matches the test files (the LM >>> is trained on the text corresponding to the audio book from which the >>> test utterances were taken - not the best practice of course). >>> >>> Vassil >>> >>> On Tue, May 14, 2013 at 2:59 PM, Mailing list used for User >>> Communication and Updates <kal...@li...> wrote: >>> > Hi Vassil, >>> > >>> > May I asked about the performance (in terms of WER/SER) of online >>> decoder? >>> > >>> > What is the expected WER for online-wav-gmm-decode-faster, >>> > if I reached with gmm-latgen-faster scores in table below? >>> > I would like to use the same trained models for >>> online-wav-gmm-decode-faster >>> > as >>> > I used for gmm-latgen-faster (and lattice-best-path). >>> > >>> > exp RT coef WER >>> > _ri3b_fmmi_b 11.33336625 19.42 >>> > tri2b_mpe 1.2307175 21.22 >>> > mono 2.8952 49.88 >>> > tri3b_mmi 1.24198625 20.01 >>> > tri1 2.398165 28.13 >>> > tri2b_mmi 1.65662125 20.34 >>> > tri2a 2.15838 28.43 >>> > tri2b 1.451105 27.96 >>> > tri3b 1.0596075 27.79 >>> > tri3b_fmmi_c 11.4361875 19.13 >>> > tri2b_mmi_b0.05 2.0089575 19.64 >>> > tri3b_fmmi_d 16.1227625 19.5 >>> > >>> > The names and the core settings of experiments are the same as in >>> > egs/voxforge/s5/run.sh >>> > >>> > >>> > With the online-wav-gmm-decode-faster >>> > I reached really bad scores due to bugs (which I still need to fix), >>> > but still also in the online demo the results are not so nice. >>> > >>> > Thanks for any help >>> > >>> > Ondra Platek >>> > >>> > >>> > On 26 April 2013 15:35, Mailing list used for User Communication and >>> Updates >>> > <kal...@li...> wrote: >>> >> >>> >> Hi, >>> >> as for taking input from a microphone you might want to have a look at >>> >> the (optional) online decoder. There is a simple demo script in >>> >> egs/voxforge/online-demo. There is also a version that can decode .wav >>> >> files without a separate feature extraction step. The code is not >>> >> extensively tested and lacks some polish and flexibility, but perhaps >>> >> you can use it as an example. >>> >> >>> >> Vassil >>> >> >>> >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User >>> >> Communication and Updates <kal...@li...> wrote: >>> >> > Dear all, >>> >> > I'm working on the development of an R&D voice-to-voice module and I >>> >> > would >>> >> > like to use Kaldi for the transcription part (we made some tests >>> with >>> >> > PocketSphinx but we found that Kaldi is more adapted for our task). >>> >> > >>> >> > The problem is that I'm not really expert in speech2text (Kaldi >>> models >>> >> > will >>> >> > be provided by another team) and I did not found scripts (or >>> plugins) >>> >> > allowing an easy integration of Kaldi : How to manage streams (with >>> >> > gstreammer for example)? how we can decode a single wav file? etc. >>> >> > >>> >> > Is someone else has already handle these problems? are there any >>> scripts >>> >> > to >>> >> > facilitate this task? >>> >> > >>> >> > thanks in advance for your reply, >>> >> > >>> >> > Best regards >>> >> > >>> >> > >>> >> > >>> >> > >>> ------------------------------------------------------------------------------ >>> >> > Try New Relic Now & We'll Send You this Cool Shirt >>> >> > New Relic is the only SaaS-based application performance monitoring >>> >> > service >>> >> > that delivers powerful full stack analytics. Optimize and monitor >>> your >>> >> > browser, app, & servers with just a few lines of code. Try New Relic >>> >> > and get this awesome Nerd Life shirt! >>> >> > http://p.sf.net/sfu/newrelic_d2d_apr >>> >> > _______________________________________________ >>> >> > Kaldi-users mailing list >>> >> > Kal...@li... >>> >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> >> > >>> >> >>> >> >>> >> >>> ------------------------------------------------------------------------------ >>> >> Try New Relic Now & We'll Send You this Cool Shirt >>> >> New Relic is the only SaaS-based application performance monitoring >>> >> service >>> >> that delivers powerful full stack analytics. Optimize and monitor your >>> >> browser, app, & servers with just a few lines of code. Try New Relic >>> >> and get this awesome Nerd Life shirt! >>> http://p.sf.net/sfu/newrelic_d2d_apr >>> >> _______________________________________________ >>> >> Kaldi-users mailing list >>> >> Kal...@li... >>> >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> > >>> > >>> > >>> > >>> ------------------------------------------------------------------------------ >>> > AlienVault Unified Security Management (USM) platform delivers complete >>> > security visibility with the essential security capabilities. Easily >>> and >>> > efficiently configure, manage, and operate all of your security >>> controls >>> > from a single console and one unified framework. Download a free trial. >>> > http://p.sf.net/sfu/alienvault_d2d >>> > _______________________________________________ >>> > Kaldi-users mailing list >>> > Kal...@li... >>> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> > >>> >>> >>> ------------------------------------------------------------------------------ >>> AlienVault Unified Security Management (USM) platform delivers complete >>> security visibility with the essential security capabilities. Easily and >>> efficiently configure, manage, and operate all of your security controls >>> from a single console and one unified framework. Download a free trial. >>> http://p.sf.net/sfu/alienvault_d2d >>> _______________________________________________ >>> Kaldi-users mailing list >>> Kal...@li... >>> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> >> >> >> >> ------------------------------------------------------------------------------ >> AlienVault Unified Security Management (USM) platform delivers complete >> security visibility with the essential security capabilities. Easily and >> efficiently configure, manage, and operate all of your security controls >> from a single console and one unified framework. Download a free trial. >> http://p.sf.net/sfu/alienvault_d2d >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> >> > > > ------------------------------------------------------------------------------ > AlienVault Unified Security Management (USM) platform delivers complete > security visibility with the essential security capabilities. Easily and > efficiently configure, manage, and operate all of your security controls > from a single console and one unified framework. Download a free trial. > http://p.sf.net/sfu/alienvault_d2d > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 16:10:00
|
You have to be careful that you give the online decoder the right options corresponding tot the features that you used. See if there are any non-default options in your MFCC extraction or PLP extraction, for instance, and that the LDA window is set correctly. Dan On Tue, May 14, 2013 at 10:10 AM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > As I said on my data have results like 70% WER. It is due to some bug, > which I have not fixed yet. > > In the online demo I tried to use our test (quite general data - in terms > of LM) and test it against online demo, > because as far as I understood it the online demo was trained on the same > data which are in supplied as the test data. > > Basically, I was asking for the numbers because I need to know if I have > still bug in my script or it is just normal performance. > > Thansk > > Ondra > > > > > On 14 May 2013 15:39, Mailing list used for User Communication and Updates > <kal...@li...> wrote: > >> Hi, >> >> I don't have specific numbers to share (as I said the online decoder >> is not rigorously tested as far as I know). In principle I think the >> online decoder should perform slightly worse than the offline versions >> due to things like online CMN computation. >> >> What do you mean exactly when you say that the results for the online >> demo are not so good? As far as I remember the WER for the test WAV >> files was about 7%, which is not so bad as today's speech recognition >> goes. Of course the WER in this case is so low, because the language >> model is relatively small and perfectly matches the test files (the LM >> is trained on the text corresponding to the audio book from which the >> test utterances were taken - not the best practice of course). >> >> Vassil >> >> On Tue, May 14, 2013 at 2:59 PM, Mailing list used for User >> Communication and Updates <kal...@li...> wrote: >> > Hi Vassil, >> > >> > May I asked about the performance (in terms of WER/SER) of online >> decoder? >> > >> > What is the expected WER for online-wav-gmm-decode-faster, >> > if I reached with gmm-latgen-faster scores in table below? >> > I would like to use the same trained models for >> online-wav-gmm-decode-faster >> > as >> > I used for gmm-latgen-faster (and lattice-best-path). >> > >> > exp RT coef WER >> > _ri3b_fmmi_b 11.33336625 19.42 >> > tri2b_mpe 1.2307175 21.22 >> > mono 2.8952 49.88 >> > tri3b_mmi 1.24198625 20.01 >> > tri1 2.398165 28.13 >> > tri2b_mmi 1.65662125 20.34 >> > tri2a 2.15838 28.43 >> > tri2b 1.451105 27.96 >> > tri3b 1.0596075 27.79 >> > tri3b_fmmi_c 11.4361875 19.13 >> > tri2b_mmi_b0.05 2.0089575 19.64 >> > tri3b_fmmi_d 16.1227625 19.5 >> > >> > The names and the core settings of experiments are the same as in >> > egs/voxforge/s5/run.sh >> > >> > >> > With the online-wav-gmm-decode-faster >> > I reached really bad scores due to bugs (which I still need to fix), >> > but still also in the online demo the results are not so nice. >> > >> > Thanks for any help >> > >> > Ondra Platek >> > >> > >> > On 26 April 2013 15:35, Mailing list used for User Communication and >> Updates >> > <kal...@li...> wrote: >> >> >> >> Hi, >> >> as for taking input from a microphone you might want to have a look at >> >> the (optional) online decoder. There is a simple demo script in >> >> egs/voxforge/online-demo. There is also a version that can decode .wav >> >> files without a separate feature extraction step. The code is not >> >> extensively tested and lacks some polish and flexibility, but perhaps >> >> you can use it as an example. >> >> >> >> Vassil >> >> >> >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User >> >> Communication and Updates <kal...@li...> wrote: >> >> > Dear all, >> >> > I'm working on the development of an R&D voice-to-voice module and I >> >> > would >> >> > like to use Kaldi for the transcription part (we made some tests with >> >> > PocketSphinx but we found that Kaldi is more adapted for our task). >> >> > >> >> > The problem is that I'm not really expert in speech2text (Kaldi >> models >> >> > will >> >> > be provided by another team) and I did not found scripts (or plugins) >> >> > allowing an easy integration of Kaldi : How to manage streams (with >> >> > gstreammer for example)? how we can decode a single wav file? etc. >> >> > >> >> > Is someone else has already handle these problems? are there any >> scripts >> >> > to >> >> > facilitate this task? >> >> > >> >> > thanks in advance for your reply, >> >> > >> >> > Best regards >> >> > >> >> > >> >> > >> >> > >> ------------------------------------------------------------------------------ >> >> > Try New Relic Now & We'll Send You this Cool Shirt >> >> > New Relic is the only SaaS-based application performance monitoring >> >> > service >> >> > that delivers powerful full stack analytics. Optimize and monitor >> your >> >> > browser, app, & servers with just a few lines of code. Try New Relic >> >> > and get this awesome Nerd Life shirt! >> >> > http://p.sf.net/sfu/newrelic_d2d_apr >> >> > _______________________________________________ >> >> > Kaldi-users mailing list >> >> > Kal...@li... >> >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >> >> > >> >> >> >> >> >> >> ------------------------------------------------------------------------------ >> >> Try New Relic Now & We'll Send You this Cool Shirt >> >> New Relic is the only SaaS-based application performance monitoring >> >> service >> >> that delivers powerful full stack analytics. Optimize and monitor your >> >> browser, app, & servers with just a few lines of code. Try New Relic >> >> and get this awesome Nerd Life shirt! >> http://p.sf.net/sfu/newrelic_d2d_apr >> >> _______________________________________________ >> >> Kaldi-users mailing list >> >> Kal...@li... >> >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > >> > >> > >> > >> ------------------------------------------------------------------------------ >> > AlienVault Unified Security Management (USM) platform delivers complete >> > security visibility with the essential security capabilities. Easily and >> > efficiently configure, manage, and operate all of your security controls >> > from a single console and one unified framework. Download a free trial. >> > http://p.sf.net/sfu/alienvault_d2d >> > _______________________________________________ >> > Kaldi-users mailing list >> > Kal...@li... >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > >> >> >> ------------------------------------------------------------------------------ >> AlienVault Unified Security Management (USM) platform delivers complete >> security visibility with the essential security capabilities. Easily and >> efficiently configure, manage, and operate all of your security controls >> from a single console and one unified framework. Download a free trial. >> http://p.sf.net/sfu/alienvault_d2d >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > > > > ------------------------------------------------------------------------------ > AlienVault Unified Security Management (USM) platform delivers complete > security visibility with the essential security capabilities. Easily and > efficiently configure, manage, and operate all of your security controls > from a single console and one unified framework. Download a free trial. > http://p.sf.net/sfu/alienvault_d2d > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 14:10:23
|
As I said on my data have results like 70% WER. It is due to some bug, which I have not fixed yet. In the online demo I tried to use our test (quite general data - in terms of LM) and test it against online demo, because as far as I understood it the online demo was trained on the same data which are in supplied as the test data. Basically, I was asking for the numbers because I need to know if I have still bug in my script or it is just normal performance. Thansk Ondra On 14 May 2013 15:39, Mailing list used for User Communication and Updates < kal...@li...> wrote: > Hi, > > I don't have specific numbers to share (as I said the online decoder > is not rigorously tested as far as I know). In principle I think the > online decoder should perform slightly worse than the offline versions > due to things like online CMN computation. > > What do you mean exactly when you say that the results for the online > demo are not so good? As far as I remember the WER for the test WAV > files was about 7%, which is not so bad as today's speech recognition > goes. Of course the WER in this case is so low, because the language > model is relatively small and perfectly matches the test files (the LM > is trained on the text corresponding to the audio book from which the > test utterances were taken - not the best practice of course). > > Vassil > > On Tue, May 14, 2013 at 2:59 PM, Mailing list used for User > Communication and Updates <kal...@li...> wrote: > > Hi Vassil, > > > > May I asked about the performance (in terms of WER/SER) of online > decoder? > > > > What is the expected WER for online-wav-gmm-decode-faster, > > if I reached with gmm-latgen-faster scores in table below? > > I would like to use the same trained models for > online-wav-gmm-decode-faster > > as > > I used for gmm-latgen-faster (and lattice-best-path). > > > > exp RT coef WER > > _ri3b_fmmi_b 11.33336625 19.42 > > tri2b_mpe 1.2307175 21.22 > > mono 2.8952 49.88 > > tri3b_mmi 1.24198625 20.01 > > tri1 2.398165 28.13 > > tri2b_mmi 1.65662125 20.34 > > tri2a 2.15838 28.43 > > tri2b 1.451105 27.96 > > tri3b 1.0596075 27.79 > > tri3b_fmmi_c 11.4361875 19.13 > > tri2b_mmi_b0.05 2.0089575 19.64 > > tri3b_fmmi_d 16.1227625 19.5 > > > > The names and the core settings of experiments are the same as in > > egs/voxforge/s5/run.sh > > > > > > With the online-wav-gmm-decode-faster > > I reached really bad scores due to bugs (which I still need to fix), > > but still also in the online demo the results are not so nice. > > > > Thanks for any help > > > > Ondra Platek > > > > > > On 26 April 2013 15:35, Mailing list used for User Communication and > Updates > > <kal...@li...> wrote: > >> > >> Hi, > >> as for taking input from a microphone you might want to have a look at > >> the (optional) online decoder. There is a simple demo script in > >> egs/voxforge/online-demo. There is also a version that can decode .wav > >> files without a separate feature extraction step. The code is not > >> extensively tested and lacks some polish and flexibility, but perhaps > >> you can use it as an example. > >> > >> Vassil > >> > >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User > >> Communication and Updates <kal...@li...> wrote: > >> > Dear all, > >> > I'm working on the development of an R&D voice-to-voice module and I > >> > would > >> > like to use Kaldi for the transcription part (we made some tests with > >> > PocketSphinx but we found that Kaldi is more adapted for our task). > >> > > >> > The problem is that I'm not really expert in speech2text (Kaldi models > >> > will > >> > be provided by another team) and I did not found scripts (or plugins) > >> > allowing an easy integration of Kaldi : How to manage streams (with > >> > gstreammer for example)? how we can decode a single wav file? etc. > >> > > >> > Is someone else has already handle these problems? are there any > scripts > >> > to > >> > facilitate this task? > >> > > >> > thanks in advance for your reply, > >> > > >> > Best regards > >> > > >> > > >> > > >> > > ------------------------------------------------------------------------------ > >> > Try New Relic Now & We'll Send You this Cool Shirt > >> > New Relic is the only SaaS-based application performance monitoring > >> > service > >> > that delivers powerful full stack analytics. Optimize and monitor your > >> > browser, app, & servers with just a few lines of code. Try New Relic > >> > and get this awesome Nerd Life shirt! > >> > http://p.sf.net/sfu/newrelic_d2d_apr > >> > _______________________________________________ > >> > Kaldi-users mailing list > >> > Kal...@li... > >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users > >> > > >> > >> > >> > ------------------------------------------------------------------------------ > >> Try New Relic Now & We'll Send You this Cool Shirt > >> New Relic is the only SaaS-based application performance monitoring > >> service > >> that delivers powerful full stack analytics. Optimize and monitor your > >> browser, app, & servers with just a few lines of code. Try New Relic > >> and get this awesome Nerd Life shirt! > http://p.sf.net/sfu/newrelic_d2d_apr > >> _______________________________________________ > >> Kaldi-users mailing list > >> Kal...@li... > >> https://lists.sourceforge.net/lists/listinfo/kaldi-users > > > > > > > > > ------------------------------------------------------------------------------ > > AlienVault Unified Security Management (USM) platform delivers complete > > security visibility with the essential security capabilities. Easily and > > efficiently configure, manage, and operate all of your security controls > > from a single console and one unified framework. Download a free trial. > > http://p.sf.net/sfu/alienvault_d2d > > _______________________________________________ > > Kaldi-users mailing list > > Kal...@li... > > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > > > > ------------------------------------------------------------------------------ > AlienVault Unified Security Management (USM) platform delivers complete > security visibility with the essential security capabilities. Easily and > efficiently configure, manage, and operate all of your security controls > from a single console and one unified framework. Download a free trial. > http://p.sf.net/sfu/alienvault_d2d > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 13:39:35
|
Hi, I don't have specific numbers to share (as I said the online decoder is not rigorously tested as far as I know). In principle I think the online decoder should perform slightly worse than the offline versions due to things like online CMN computation. What do you mean exactly when you say that the results for the online demo are not so good? As far as I remember the WER for the test WAV files was about 7%, which is not so bad as today's speech recognition goes. Of course the WER in this case is so low, because the language model is relatively small and perfectly matches the test files (the LM is trained on the text corresponding to the audio book from which the test utterances were taken - not the best practice of course). Vassil On Tue, May 14, 2013 at 2:59 PM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > Hi Vassil, > > May I asked about the performance (in terms of WER/SER) of online decoder? > > What is the expected WER for online-wav-gmm-decode-faster, > if I reached with gmm-latgen-faster scores in table below? > I would like to use the same trained models for online-wav-gmm-decode-faster > as > I used for gmm-latgen-faster (and lattice-best-path). > > exp RT coef WER > _ri3b_fmmi_b 11.33336625 19.42 > tri2b_mpe 1.2307175 21.22 > mono 2.8952 49.88 > tri3b_mmi 1.24198625 20.01 > tri1 2.398165 28.13 > tri2b_mmi 1.65662125 20.34 > tri2a 2.15838 28.43 > tri2b 1.451105 27.96 > tri3b 1.0596075 27.79 > tri3b_fmmi_c 11.4361875 19.13 > tri2b_mmi_b0.05 2.0089575 19.64 > tri3b_fmmi_d 16.1227625 19.5 > > The names and the core settings of experiments are the same as in > egs/voxforge/s5/run.sh > > > With the online-wav-gmm-decode-faster > I reached really bad scores due to bugs (which I still need to fix), > but still also in the online demo the results are not so nice. > > Thanks for any help > > Ondra Platek > > > On 26 April 2013 15:35, Mailing list used for User Communication and Updates > <kal...@li...> wrote: >> >> Hi, >> as for taking input from a microphone you might want to have a look at >> the (optional) online decoder. There is a simple demo script in >> egs/voxforge/online-demo. There is also a version that can decode .wav >> files without a separate feature extraction step. The code is not >> extensively tested and lacks some polish and flexibility, but perhaps >> you can use it as an example. >> >> Vassil >> >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User >> Communication and Updates <kal...@li...> wrote: >> > Dear all, >> > I'm working on the development of an R&D voice-to-voice module and I >> > would >> > like to use Kaldi for the transcription part (we made some tests with >> > PocketSphinx but we found that Kaldi is more adapted for our task). >> > >> > The problem is that I'm not really expert in speech2text (Kaldi models >> > will >> > be provided by another team) and I did not found scripts (or plugins) >> > allowing an easy integration of Kaldi : How to manage streams (with >> > gstreammer for example)? how we can decode a single wav file? etc. >> > >> > Is someone else has already handle these problems? are there any scripts >> > to >> > facilitate this task? >> > >> > thanks in advance for your reply, >> > >> > Best regards >> > >> > >> > >> > ------------------------------------------------------------------------------ >> > Try New Relic Now & We'll Send You this Cool Shirt >> > New Relic is the only SaaS-based application performance monitoring >> > service >> > that delivers powerful full stack analytics. Optimize and monitor your >> > browser, app, & servers with just a few lines of code. Try New Relic >> > and get this awesome Nerd Life shirt! >> > http://p.sf.net/sfu/newrelic_d2d_apr >> > _______________________________________________ >> > Kaldi-users mailing list >> > Kal...@li... >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > >> >> >> ------------------------------------------------------------------------------ >> Try New Relic Now & We'll Send You this Cool Shirt >> New Relic is the only SaaS-based application performance monitoring >> service >> that delivers powerful full stack analytics. Optimize and monitor your >> browser, app, & servers with just a few lines of code. Try New Relic >> and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_apr >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users > > > > ------------------------------------------------------------------------------ > AlienVault Unified Security Management (USM) platform delivers complete > security visibility with the essential security capabilities. Easily and > efficiently configure, manage, and operate all of your security controls > from a single console and one unified framework. Download a free trial. > http://p.sf.net/sfu/alienvault_d2d > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 12:57:23
|
>From my experience, your online WER should be around 25 (using tri2b_mmi model), or even better than that. Haihua On Tue, May 14, 2013 at 7:59 PM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > Hi Vassil, > > May I asked about the performance (in terms of WER/SER) of online decoder? > > What is the expected WER for online-wav-gmm-decode-faster, > if I reached with gmm-latgen-faster scores in table below? > I would like to use the same trained models for > online-wav-gmm-decode-faster as > I used for gmm-latgen-faster (and lattice-best-path). > > exp RT coef WER > _ri3b_fmmi_b 11.33336625 19.42 > tri2b_mpe 1.2307175 21.22 > mono 2.8952 49.88 > tri3b_mmi 1.24198625 20.01 > tri1 2.398165 28.13 > tri2b_mmi 1.65662125 20.34 > tri2a 2.15838 28.43 > tri2b 1.451105 27.96 > tri3b 1.0596075 27.79 > tri3b_fmmi_c 11.4361875 19.13 > tri2b_mmi_b0.05 2.0089575 19.64 > tri3b_fmmi_d 16.1227625 19.5 > > The names and the core settings of experiments are the same as in > egs/voxforge/s5/run.sh > > > With the online-wav-gmm-decode-faster > I reached really bad scores due to bugs (which I still need to fix), > but still also in the online demo the results are not so nice. > > Thanks for any help > > Ondra Platek > > > On 26 April 2013 15:35, Mailing list used for User Communication and > Updates <kal...@li...> wrote: > >> Hi, >> as for taking input from a microphone you might want to have a look at >> the (optional) online decoder. There is a simple demo script in >> egs/voxforge/online-demo. There is also a version that can decode .wav >> files without a separate feature extraction step. The code is not >> extensively tested and lacks some polish and flexibility, but perhaps >> you can use it as an example. >> >> Vassil >> >> On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User >> Communication and Updates <kal...@li...> wrote: >> > Dear all, >> > I'm working on the development of an R&D voice-to-voice module and I >> would >> > like to use Kaldi for the transcription part (we made some tests with >> > PocketSphinx but we found that Kaldi is more adapted for our task). >> > >> > The problem is that I'm not really expert in speech2text (Kaldi models >> will >> > be provided by another team) and I did not found scripts (or plugins) >> > allowing an easy integration of Kaldi : How to manage streams (with >> > gstreammer for example)? how we can decode a single wav file? etc. >> > >> > Is someone else has already handle these problems? are there any >> scripts to >> > facilitate this task? >> > >> > thanks in advance for your reply, >> > >> > Best regards >> > >> > >> > >> ------------------------------------------------------------------------------ >> > Try New Relic Now & We'll Send You this Cool Shirt >> > New Relic is the only SaaS-based application performance monitoring >> service >> > that delivers powerful full stack analytics. Optimize and monitor your >> > browser, app, & servers with just a few lines of code. Try New Relic >> > and get this awesome Nerd Life shirt! >> http://p.sf.net/sfu/newrelic_d2d_apr >> > _______________________________________________ >> > Kaldi-users mailing list >> > Kal...@li... >> > https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > >> >> >> ------------------------------------------------------------------------------ >> Try New Relic Now & We'll Send You this Cool Shirt >> New Relic is the only SaaS-based application performance monitoring >> service >> that delivers powerful full stack analytics. Optimize and monitor your >> browser, app, & servers with just a few lines of code. Try New Relic >> and get this awesome Nerd Life shirt! >> http://p.sf.net/sfu/newrelic_d2d_apr >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > > > > ------------------------------------------------------------------------------ > AlienVault Unified Security Management (USM) platform delivers complete > security visibility with the essential security capabilities. Easily and > efficiently configure, manage, and operate all of your security controls > from a single console and one unified framework. Download a free trial. > http://p.sf.net/sfu/alienvault_d2d > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-14 11:59:21
|
Hi Vassil, May I asked about the performance (in terms of WER/SER) of online decoder? What is the expected WER for online-wav-gmm-decode-faster, if I reached with gmm-latgen-faster scores in table below? I would like to use the same trained models for online-wav-gmm-decode-faster as I used for gmm-latgen-faster (and lattice-best-path). exp RT coef WER _ri3b_fmmi_b 11.33336625 19.42 tri2b_mpe 1.2307175 21.22 mono 2.8952 49.88 tri3b_mmi 1.24198625 20.01 tri1 2.398165 28.13 tri2b_mmi 1.65662125 20.34 tri2a 2.15838 28.43 tri2b 1.451105 27.96 tri3b 1.0596075 27.79 tri3b_fmmi_c 11.4361875 19.13 tri2b_mmi_b0.05 2.0089575 19.64 tri3b_fmmi_d 16.1227625 19.5 The names and the core settings of experiments are the same as in egs/voxforge/s5/run.sh With the online-wav-gmm-decode-faster I reached really bad scores due to bugs (which I still need to fix), but still also in the online demo the results are not so nice. Thanks for any help Ondra Platek On 26 April 2013 15:35, Mailing list used for User Communication and Updates <kal...@li...> wrote: > Hi, > as for taking input from a microphone you might want to have a look at > the (optional) online decoder. There is a simple demo script in > egs/voxforge/online-demo. There is also a version that can decode .wav > files without a separate feature extraction step. The code is not > extensively tested and lacks some polish and flexibility, but perhaps > you can use it as an example. > > Vassil > > On Fri, Apr 26, 2013 at 3:55 PM, Mailing list used for User > Communication and Updates <kal...@li...> wrote: > > Dear all, > > I'm working on the development of an R&D voice-to-voice module and I > would > > like to use Kaldi for the transcription part (we made some tests with > > PocketSphinx but we found that Kaldi is more adapted for our task). > > > > The problem is that I'm not really expert in speech2text (Kaldi models > will > > be provided by another team) and I did not found scripts (or plugins) > > allowing an easy integration of Kaldi : How to manage streams (with > > gstreammer for example)? how we can decode a single wav file? etc. > > > > Is someone else has already handle these problems? are there any scripts > to > > facilitate this task? > > > > thanks in advance for your reply, > > > > Best regards > > > > > > > ------------------------------------------------------------------------------ > > Try New Relic Now & We'll Send You this Cool Shirt > > New Relic is the only SaaS-based application performance monitoring > service > > that delivers powerful full stack analytics. Optimize and monitor your > > browser, app, & servers with just a few lines of code. Try New Relic > > and get this awesome Nerd Life shirt! > http://p.sf.net/sfu/newrelic_d2d_apr > > _______________________________________________ > > Kaldi-users mailing list > > Kal...@li... > > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > > > > ------------------------------------------------------------------------------ > Try New Relic Now & We'll Send You this Cool Shirt > New Relic is the only SaaS-based application performance monitoring service > that delivers powerful full stack analytics. Optimize and monitor your > browser, app, & servers with just a few lines of code. Try New Relic > and get this awesome Nerd Life shirt! http://p.sf.net/sfu/newrelic_d2d_apr > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 18:48:46
|
Thanks for that. Here's what I have: Opensuse uses Yast as a package manager and has libraries for both atlas and openblas. I did try installing atlas before, but I was thrown by the fact that no libatlas.so is provided. However there is a reason for my confusion. Opensuse packages provide both libsatlas and libtatlas so files. Evidently the 's' version is compiled for serial and the 't' version is for threaded. I think the latter is if you have a CUDA card installed. I added a symlink in /usr/lib64 for libatlas.so pointing at atlas/libsatlas.so (conservatively, this can be changed) and this allows configure to finish. There are some warnings about it being the wrong architecture, but so far make is running. I'm pretty sure I went through something similar to this in getting numpy and octave installed. All good practice, and plenty of hard drive space. Thank you for your prompt assistance. If I can return the favour sometime let me know. On 05/08/2013 02:05 PM, Mailing list used for User Communication and Updates wrote: > OK, it's complaining because you have no ATLAS package installed on your > system (or it doesn't know where to find it because we haven't worked > much with Suse). Compiling ATLAS tends to be tricky; this is inherent > to the way ATLAS works. > You could try installing OpenBlas (try "make openblas" in tools/) and > give suitable flags to "configure" in src. > Or you could find a suitable package for Atlas (does suse have a notion > of packages?) > Dan > > > On Wed, May 8, 2013 at 2:03 PM, Mailing list used for User Communication > and Updates <kal...@li... > <mailto:kal...@li...>> wrote: > > > > On 05/08/2013 12:53 PM, Daniel Povey wrote: > > Oh, OK. > > I have just committed some changes in the tools/ directory, > including a > > change to the Makefile that should automatically create a link from > > lib64 to lib. Colin, try doing "make" again in tools/ > > Dan > > > > Some good news, so I deleted the rest of the conversation. Did svn > update and the symlink from lib64 to lib is created. Now ./configure in > src gets past the libfst thing. So the symlink from one dir to another > seems to work well compared to symlinking individual files. > > Now stops at: > > Could not find libatlas.so in any of the obvious places. > > $ ls ../tools/ATLAS/ > include > > otherwise empty. > > I think it is traditional not to shoot the messenger. > Part of the output from the configure is advice to run install_atlas.sh > so I did that and this filled in a lot of directories alongside > /include/, but ended in error > > cp: cannot stat > ‘/home/colin/kaldi-trunk/tools/ATLAS/build/lib/libtatlas.so’: No such > file or directory > make[1]: [install_lib] Error 1 (ignored) > make[1]: Leaving directory `/home/colin/kaldi-trunk/tools/ATLAS/build' > > My first thought was just to do another make output file, but since, as > you are probably aware, the output from this command is huge, perhaps > you have a suggestion as to the shortest path from here. > > -- > --- > Colin Beckingham > 613-454-5369 <tel:613-454-5369> > http://www.it4gh.com > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > <mailto:Kal...@li...> > https://lists.sourceforge.net/lists/listinfo/kaldi-users > > > > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > > > > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 18:05:31
|
OK, it's complaining because you have no ATLAS package installed on your system (or it doesn't know where to find it because we haven't worked much with Suse). Compiling ATLAS tends to be tricky; this is inherent to the way ATLAS works. You could try installing OpenBlas (try "make openblas" in tools/) and give suitable flags to "configure" in src. Or you could find a suitable package for Atlas (does suse have a notion of packages?) Dan On Wed, May 8, 2013 at 2:03 PM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > > > On 05/08/2013 12:53 PM, Daniel Povey wrote: > > Oh, OK. > > I have just committed some changes in the tools/ directory, including a > > change to the Makefile that should automatically create a link from > > lib64 to lib. Colin, try doing "make" again in tools/ > > Dan > > > > Some good news, so I deleted the rest of the conversation. Did svn > update and the symlink from lib64 to lib is created. Now ./configure in > src gets past the libfst thing. So the symlink from one dir to another > seems to work well compared to symlinking individual files. > > Now stops at: > > Could not find libatlas.so in any of the obvious places. > > $ ls ../tools/ATLAS/ > include > > otherwise empty. > > I think it is traditional not to shoot the messenger. > Part of the output from the configure is advice to run install_atlas.sh > so I did that and this filled in a lot of directories alongside > /include/, but ended in error > > cp: cannot stat > ‘/home/colin/kaldi-trunk/tools/ATLAS/build/lib/libtatlas.so’: No such > file or directory > make[1]: [install_lib] Error 1 (ignored) > make[1]: Leaving directory `/home/colin/kaldi-trunk/tools/ATLAS/build' > > My first thought was just to do another make output file, but since, as > you are probably aware, the output from this command is huge, perhaps > you have a suggestion as to the shortest path from here. > > -- > --- > Colin Beckingham > 613-454-5369 > http://www.it4gh.com > > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 18:02:57
|
On 05/08/2013 12:53 PM, Daniel Povey wrote: > Oh, OK. > I have just committed some changes in the tools/ directory, including a > change to the Makefile that should automatically create a link from > lib64 to lib. Colin, try doing "make" again in tools/ > Dan > Some good news, so I deleted the rest of the conversation. Did svn update and the symlink from lib64 to lib is created. Now ./configure in src gets past the libfst thing. So the symlink from one dir to another seems to work well compared to symlinking individual files. Now stops at: Could not find libatlas.so in any of the obvious places. $ ls ../tools/ATLAS/ include otherwise empty. I think it is traditional not to shoot the messenger. Part of the output from the configure is advice to run install_atlas.sh so I did that and this filled in a lot of directories alongside /include/, but ended in error cp: cannot stat ‘/home/colin/kaldi-trunk/tools/ATLAS/build/lib/libtatlas.so’: No such file or directory make[1]: [install_lib] Error 1 (ignored) make[1]: Leaving directory `/home/colin/kaldi-trunk/tools/ATLAS/build' My first thought was just to do another make output file, but since, as you are probably aware, the output from this command is huge, perhaps you have a suggestion as to the shortest path from here. -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 16:29:00
|
OK, this is weird. It seems to have compiled the extensions but not the core library. Cc'ing Mike Riley. Mike-- he is compiling OpenFst version 1.3.2 on Opensuse 12.3 64 bit, kernel 3.9; it is configured with ./configure --prefix=`pwd` --enable-static --disable-shared --enable-far --enable-ngram-fsts and it acts like it is happily installing the libraries but it only installs the extensions. I'll separately forward you the output of his configure and make. Dan On Wed, May 8, 2013 at 12:23 PM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > > > On 05/08/2013 12:15 PM, Mailing list used for User Communication and > Updates wrote: > > It says in the output you sent me, > > > > Libraries have been installed in: > > /home/colin/kaldi-trunk/tools/openfst-1.3.2/lib64/fst > > > > Can you do a ls -l of that directory? What did it install there? It > > seems to think it installed something. > > > > Dan > > > > > > > > On Wed, May 8, 2013 at 12:02 PM, Daniel Povey <dp...@gm... > > <mailto:dp...@gm...>> wrote: > > > > I could not figure out how to authorize the message, it rejected my > > password. Please send it to dp...@gm... <mailto: > dp...@gm...> > > Dan > > > > > > > > On Wed, May 8, 2013 at 11:42 AM, Mailing list used for User > > Communication and Updates <kal...@li... > > <mailto:kal...@li...>> wrote: > > > > > > > > On 05/08/2013 10:59 AM, Mailing list used for User Communication > and > > Updates wrote: > > > Try doing "make" in the tools/ directory and redirect the > > output to a > > > file, e.g. make >& foo > > > and paste the file into the email, something seems to have > > gone wrong. > > > The symlinks should be automatically created and regardless > > you should > > > have an openfst.a file > > > Dan > > > > > > > > > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User > > > Communication and Updates <kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>>> wrote: > > > > > > > > > > > > On 05/08/2013 10:34 AM, Mailing list used for User > > Communication and > > > Updates wrote: > > > > Actually, the problem might also be that the "make > > install" part > > > of the > > > > OpenFST installation failed, because there should be a > > file > > > > openfst-1.3.2/lib/openfst.a > > > > Type "make openfst_tgt" in the tools/ directory and > > see what happens > > > > Dan > > > > > > > > > > > > > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey > > <dp...@gm... <mailto:dp...@gm...> > > > <mailto:dp...@gm... <mailto:dp...@gm...>> > > > > <mailto:dp...@gm... <mailto:dp...@gm...> > > <mailto:dp...@gm... <mailto:dp...@gm...>>>> wrote: > > > > > > > > There should be a soft link from "openfst" to > > > "openfst-1.3.2". See > > > > if it exists and try to figure out why not, if it > > does not. > > > > Dan > > > > > > > > > > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used > > for User > > > > Communication and Updates > > <kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>> > > > > <mailto:kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>>>> wrote: > > > > > > > > > > > > > > > > On 05/08/2013 10:10 AM, Mailing list used for > User > > > Communication and > > > > Updates wrote: > > > > > On Wed, May 8, 2013 at 2:52 PM, Mailing > > list used for User > > > > > Communication and Updates > > > <kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>> > > > > <mailto:kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>>>> wrote: > > > > >> Using Opensuse 12.3 64 bit, kernel 3.9. > > > > >> > > > > >> 1. I issued svn co > > > svn://svn.code.sf.net/p/kaldi/code/trunk > > <http://svn.code.sf.net/p/kaldi/code/trunk> > > > <http://svn.code.sf.net/p/kaldi/code/trunk> > > > > <http://svn.code.sf.net/p/kaldi/code/trunk> > > kaldi-trunk > > > > >> 2. download appeared to finish correctly > > > > >> 3. examined INSTALL, went into dir /tools > > and did make, > > > > finished without > > > > >> error as far as I can tell > > > > >> 4. then ../src and ./configure, which > stops at > > > > >> > > > > >> $ ./configure > > > > >> Configuring ... > > > > >> Checking OpenFST library in > > > > /home/colin/kaldi-trunk/tools/openfst ... > > > > >> Checking OpenFst library was patched. > > > > >> Doing OS specific configurations ... > > > > >> ***configure failed: Static OpenFST > > library not > > > found: See > > > > >> ../tools/INSTALL *** > > > > > > > > > > Could you check to see if you have the > > following file > > > > > kaldi-trunk/tools/openfst/lib/libfst.a? > > Normally > > > typing make > > > > in the > > > > > tools directory should create it, unless > > there was > > > some error > > > > that > > > > > didn't get reported. > > > > > > > > > > > > > $ find ./ -name libfst.a > > > > ./tools/openfst-1.3.2/lib64/libfst.a > > > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > > > > > > > > > "$ find ./ -name openfst.a" does not find anything. > > > > > > Did "make openfst_tgt" which completed successfully and > > created a bunch > > > of stuff. Repeated the two searches and no change to > either. > > > > > > Will now try the symlink stuff. Thanks. > > > > > > > Dan, I did the re-make and it is on the way to the list. The > > complete > > reply was stopped by the bouncer waiting for mod since it thinks > the > > message is too big. > > > > In short, still no openfst.a. Thanks. > > > > Here is the output: > > ~/kaldi-trunk/tools/openfst-1.3.2]$ ls -l lib64/fst/ > total 29808 > -rw-r--r-- 1 colin users 141070 May 8 11:25 libfstfar.a > -rwxr-xr-x 1 colin users 936 May 8 11:25 libfstfar.la > -rw-r--r-- 1 colin users 20048824 May 8 11:25 libfstfarscript.a > -rwxr-xr-x 1 colin users 954 May 8 11:25 libfstfarscript.la > -rw-r--r-- 1 colin users 5155114 May 8 11:25 libfstngram.a > -rwxr-xr-x 1 colin users 942 May 8 11:25 libfstngram.la > -rw-r--r-- 1 colin users 5155114 May 8 11:25 ngram-fst.a > -rwxr-xr-x 1 colin users 937 May 8 11:25 ngram-fst.la > > > -- > --- > Colin Beckingham > 613-454-5369 > http://www.it4gh.com > > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 16:26:09
|
On 05/08/2013 12:16 PM, Mailing list used for User Communication and Updates wrote: > Sorry, it should be libfst.a not openfst.a > See if the configure in src/ works now. > Dan > > > > On Wed, May 8, 2013 at 12:15 PM, Daniel Povey <dp...@gm... > <mailto:dp...@gm...>> wrote: > > It says in the output you sent me, > > Libraries have been installed in: > /home/colin/kaldi-trunk/tools/openfst-1.3.2/lib64/fst > > Can you do a ls -l of that directory? What did it install there? > It seems to think it installed something. > > Dan > > > > On Wed, May 8, 2013 at 12:02 PM, Daniel Povey <dp...@gm... > <mailto:dp...@gm...>> wrote: > > I could not figure out how to authorize the message, it rejected > my password. Please send it to dp...@gm... > <mailto:dp...@gm...> > Dan > > > > On Wed, May 8, 2013 at 11:42 AM, Mailing list used for User > Communication and Updates <kal...@li... > <mailto:kal...@li...>> wrote: > > > > On 05/08/2013 10:59 AM, Mailing list used for User > Communication and > Updates wrote: > > Try doing "make" in the tools/ directory and redirect the > output to a > > file, e.g. make >& foo > > and paste the file into the email, something seems to > have gone wrong. > > The symlinks should be automatically created and > regardless you should > > have an openfst.a file > > Dan > > > > > > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User > > Communication and Updates > <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>> wrote: > > > > > > > > On 05/08/2013 10:34 AM, Mailing list used for User > Communication and > > Updates wrote: > > > Actually, the problem might also be that the "make > install" part > > of the > > > OpenFST installation failed, because there should > be a file > > > openfst-1.3.2/lib/openfst.a > > > Type "make openfst_tgt" in the tools/ directory > and see what happens > > > Dan > > > > > > > > > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey > <dp...@gm... <mailto:dp...@gm...> > > <mailto:dp...@gm... <mailto:dp...@gm...>> > > > <mailto:dp...@gm... <mailto:dp...@gm...> > <mailto:dp...@gm... <mailto:dp...@gm...>>>> wrote: > > > > > > There should be a soft link from "openfst" to > > "openfst-1.3.2". See > > > if it exists and try to figure out why not, if > it does not. > > > Dan > > > > > > > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list > used for User > > > Communication and Updates > <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>> > > > <mailto:kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>>> wrote: > > > > > > > > > > > > On 05/08/2013 10:10 AM, Mailing list used > for User > > Communication and > > > Updates wrote: > > > > On Wed, May 8, 2013 at 2:52 PM, Mailing > list used for User > > > > Communication and Updates > > <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>> > > > <mailto:kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>>> wrote: > > > >> Using Opensuse 12.3 64 bit, kernel 3.9. > > > >> > > > >> 1. I issued svn co > > svn://svn.code.sf.net/p/kaldi/code/trunk > <http://svn.code.sf.net/p/kaldi/code/trunk> > > <http://svn.code.sf.net/p/kaldi/code/trunk> > > > > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk > > > >> 2. download appeared to finish correctly > > > >> 3. examined INSTALL, went into dir > /tools and did make, > > > finished without > > > >> error as far as I can tell > > > >> 4. then ../src and ./configure, which > stops at > > > >> > > > >> $ ./configure > > > >> Configuring ... > > > >> Checking OpenFST library in > > > /home/colin/kaldi-trunk/tools/openfst ... > > > >> Checking OpenFst library was patched. > > > >> Doing OS specific configurations ... > > > >> ***configure failed: Static OpenFST > library not > > found: See > > > >> ../tools/INSTALL *** > > > > > > > > Could you check to see if you have the > following file > > > > kaldi-trunk/tools/openfst/lib/libfst.a? > Normally > > typing make > > > in the > > > > tools directory should create it, > unless there was > > some error > > > that > > > > didn't get reported. > > > > > > > > > > $ find ./ -name libfst.a > > > ./tools/openfst-1.3.2/lib64/libfst.a > > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > > > > > > "$ find ./ -name openfst.a" does not find anything. > > > > Did "make openfst_tgt" which completed successfully > and created a bunch > > of stuff. Repeated the two searches and no change to > either. > > > > Will now try the symlink stuff. Thanks. > > > > Dan, I did the re-make and it is on the way to the list. The > complete > reply was stopped by the bouncer waiting for mod since it > thinks the > message is too big. > > In short, still no openfst.a. Thanks. > $ find ./ -name libfst.a ./tools/openfst-1.3.2/lib64/libfst.a ./tools/openfst-1.3.2/src/lib/.libs/libfst.a [colin@linux-3btt ~/kaldi-trunk]$ cd src [colin@linux-3btt ~/kaldi-trunk/src]$ ./configure Configuring ... Checking OpenFST library in /home/colin/kaldi-trunk/tools/openfst ... Checking OpenFst library was patched. Doing OS specific configurations ... ***configure failed: Static OpenFST library not found: See ../tools/INSTALL *** -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 16:23:19
|
On 05/08/2013 12:15 PM, Mailing list used for User Communication and Updates wrote: > It says in the output you sent me, > > Libraries have been installed in: > /home/colin/kaldi-trunk/tools/openfst-1.3.2/lib64/fst > > Can you do a ls -l of that directory? What did it install there? It > seems to think it installed something. > > Dan > > > > On Wed, May 8, 2013 at 12:02 PM, Daniel Povey <dp...@gm... > <mailto:dp...@gm...>> wrote: > > I could not figure out how to authorize the message, it rejected my > password. Please send it to dp...@gm... <mailto:dp...@gm...> > Dan > > > > On Wed, May 8, 2013 at 11:42 AM, Mailing list used for User > Communication and Updates <kal...@li... > <mailto:kal...@li...>> wrote: > > > > On 05/08/2013 10:59 AM, Mailing list used for User Communication and > Updates wrote: > > Try doing "make" in the tools/ directory and redirect the > output to a > > file, e.g. make >& foo > > and paste the file into the email, something seems to have > gone wrong. > > The symlinks should be automatically created and regardless > you should > > have an openfst.a file > > Dan > > > > > > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User > > Communication and Updates <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>> wrote: > > > > > > > > On 05/08/2013 10:34 AM, Mailing list used for User > Communication and > > Updates wrote: > > > Actually, the problem might also be that the "make > install" part > > of the > > > OpenFST installation failed, because there should be a > file > > > openfst-1.3.2/lib/openfst.a > > > Type "make openfst_tgt" in the tools/ directory and > see what happens > > > Dan > > > > > > > > > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey > <dp...@gm... <mailto:dp...@gm...> > > <mailto:dp...@gm... <mailto:dp...@gm...>> > > > <mailto:dp...@gm... <mailto:dp...@gm...> > <mailto:dp...@gm... <mailto:dp...@gm...>>>> wrote: > > > > > > There should be a soft link from "openfst" to > > "openfst-1.3.2". See > > > if it exists and try to figure out why not, if it > does not. > > > Dan > > > > > > > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used > for User > > > Communication and Updates > <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>> > > > <mailto:kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>>> wrote: > > > > > > > > > > > > On 05/08/2013 10:10 AM, Mailing list used for User > > Communication and > > > Updates wrote: > > > > On Wed, May 8, 2013 at 2:52 PM, Mailing > list used for User > > > > Communication and Updates > > <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>> > > > <mailto:kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>>> wrote: > > > >> Using Opensuse 12.3 64 bit, kernel 3.9. > > > >> > > > >> 1. I issued svn co > > svn://svn.code.sf.net/p/kaldi/code/trunk > <http://svn.code.sf.net/p/kaldi/code/trunk> > > <http://svn.code.sf.net/p/kaldi/code/trunk> > > > <http://svn.code.sf.net/p/kaldi/code/trunk> > kaldi-trunk > > > >> 2. download appeared to finish correctly > > > >> 3. examined INSTALL, went into dir /tools > and did make, > > > finished without > > > >> error as far as I can tell > > > >> 4. then ../src and ./configure, which stops at > > > >> > > > >> $ ./configure > > > >> Configuring ... > > > >> Checking OpenFST library in > > > /home/colin/kaldi-trunk/tools/openfst ... > > > >> Checking OpenFst library was patched. > > > >> Doing OS specific configurations ... > > > >> ***configure failed: Static OpenFST > library not > > found: See > > > >> ../tools/INSTALL *** > > > > > > > > Could you check to see if you have the > following file > > > > kaldi-trunk/tools/openfst/lib/libfst.a? > Normally > > typing make > > > in the > > > > tools directory should create it, unless > there was > > some error > > > that > > > > didn't get reported. > > > > > > > > > > $ find ./ -name libfst.a > > > ./tools/openfst-1.3.2/lib64/libfst.a > > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > > > > > > "$ find ./ -name openfst.a" does not find anything. > > > > Did "make openfst_tgt" which completed successfully and > created a bunch > > of stuff. Repeated the two searches and no change to either. > > > > Will now try the symlink stuff. Thanks. > > > > Dan, I did the re-make and it is on the way to the list. The > complete > reply was stopped by the bouncer waiting for mod since it thinks the > message is too big. > > In short, still no openfst.a. Thanks. > Here is the output: ~/kaldi-trunk/tools/openfst-1.3.2]$ ls -l lib64/fst/ total 29808 -rw-r--r-- 1 colin users 141070 May 8 11:25 libfstfar.a -rwxr-xr-x 1 colin users 936 May 8 11:25 libfstfar.la -rw-r--r-- 1 colin users 20048824 May 8 11:25 libfstfarscript.a -rwxr-xr-x 1 colin users 954 May 8 11:25 libfstfarscript.la -rw-r--r-- 1 colin users 5155114 May 8 11:25 libfstngram.a -rwxr-xr-x 1 colin users 942 May 8 11:25 libfstngram.la -rw-r--r-- 1 colin users 5155114 May 8 11:25 ngram-fst.a -rwxr-xr-x 1 colin users 937 May 8 11:25 ngram-fst.la -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 16:17:05
|
Sorry, it should be libfst.a not openfst.a See if the configure in src/ works now. Dan On Wed, May 8, 2013 at 12:15 PM, Daniel Povey <dp...@gm...> wrote: > It says in the output you sent me, > > Libraries have been installed in: > /home/colin/kaldi-trunk/tools/openfst-1.3.2/lib64/fst > > Can you do a ls -l of that directory? What did it install there? It > seems to think it installed something. > > Dan > > > > On Wed, May 8, 2013 at 12:02 PM, Daniel Povey <dp...@gm...> wrote: > >> I could not figure out how to authorize the message, it rejected my >> password. Please send it to dp...@gm... >> Dan >> >> >> >> On Wed, May 8, 2013 at 11:42 AM, Mailing list used for User Communication >> and Updates <kal...@li...> wrote: >> >>> >>> >>> On 05/08/2013 10:59 AM, Mailing list used for User Communication and >>> Updates wrote: >>> > Try doing "make" in the tools/ directory and redirect the output to a >>> > file, e.g. make >& foo >>> > and paste the file into the email, something seems to have gone wrong. >>> > The symlinks should be automatically created and regardless you should >>> > have an openfst.a file >>> > Dan >>> > >>> > >>> > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User >>> > Communication and Updates <kal...@li... >>> > <mailto:kal...@li...>> wrote: >>> > >>> > >>> > >>> > On 05/08/2013 10:34 AM, Mailing list used for User Communication >>> and >>> > Updates wrote: >>> > > Actually, the problem might also be that the "make install" part >>> > of the >>> > > OpenFST installation failed, because there should be a file >>> > > openfst-1.3.2/lib/openfst.a >>> > > Type "make openfst_tgt" in the tools/ directory and see what >>> happens >>> > > Dan >>> > > >>> > > >>> > > >>> > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm... >>> > <mailto:dp...@gm...> >>> > > <mailto:dp...@gm... <mailto:dp...@gm...>>> wrote: >>> > > >>> > > There should be a soft link from "openfst" to >>> > "openfst-1.3.2". See >>> > > if it exists and try to figure out why not, if it does not. >>> > > Dan >>> > > >>> > > >>> > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User >>> > > Communication and Updates < >>> kal...@li... >>> > <mailto:kal...@li...> >>> > > <mailto:kal...@li... >>> > <mailto:kal...@li...>>> wrote: >>> > > >>> > > >>> > > >>> > > On 05/08/2013 10:10 AM, Mailing list used for User >>> > Communication and >>> > > Updates wrote: >>> > > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used >>> for User >>> > > > Communication and Updates >>> > <kal...@li... >>> > <mailto:kal...@li...> >>> > > <mailto:kal...@li... >>> > <mailto:kal...@li...>>> wrote: >>> > > >> Using Opensuse 12.3 64 bit, kernel 3.9. >>> > > >> >>> > > >> 1. I issued svn co >>> > svn://svn.code.sf.net/p/kaldi/code/trunk >>> > <http://svn.code.sf.net/p/kaldi/code/trunk> >>> > > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk >>> > > >> 2. download appeared to finish correctly >>> > > >> 3. examined INSTALL, went into dir /tools and did >>> make, >>> > > finished without >>> > > >> error as far as I can tell >>> > > >> 4. then ../src and ./configure, which stops at >>> > > >> >>> > > >> $ ./configure >>> > > >> Configuring ... >>> > > >> Checking OpenFST library in >>> > > /home/colin/kaldi-trunk/tools/openfst ... >>> > > >> Checking OpenFst library was patched. >>> > > >> Doing OS specific configurations ... >>> > > >> ***configure failed: Static OpenFST library not >>> > found: See >>> > > >> ../tools/INSTALL *** >>> > > > >>> > > > Could you check to see if you have the following file >>> > > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally >>> > typing make >>> > > in the >>> > > > tools directory should create it, unless there was >>> > some error >>> > > that >>> > > > didn't get reported. >>> > > > >>> > > >>> > > $ find ./ -name libfst.a >>> > > ./tools/openfst-1.3.2/lib64/libfst.a >>> > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a >>> > > >>> > >>> > "$ find ./ -name openfst.a" does not find anything. >>> > >>> > Did "make openfst_tgt" which completed successfully and created a >>> bunch >>> > of stuff. Repeated the two searches and no change to either. >>> > >>> > Will now try the symlink stuff. Thanks. >>> > >>> >>> Dan, I did the re-make and it is on the way to the list. The complete >>> reply was stopped by the bouncer waiting for mod since it thinks the >>> message is too big. >>> >>> In short, still no openfst.a. Thanks. >>> >>> -- >>> --- >>> Colin Beckingham >>> 613-454-5369 >>> http://www.it4gh.com >>> >>> >>> ------------------------------------------------------------------------------ >>> Learn Graph Databases - Download FREE O'Reilly Book >>> "Graph Databases" is the definitive new guide to graph databases and >>> their applications. This 200-page book is written by three acclaimed >>> leaders in the field. The early access version is available now. >>> Download your free book today! http://p.sf.net/sfu/neotech_d2d_may >>> _______________________________________________ >>> Kaldi-users mailing list >>> Kal...@li... >>> https://lists.sourceforge.net/lists/listinfo/kaldi-users >>> >> >> > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 16:15:55
|
It says in the output you sent me, Libraries have been installed in: /home/colin/kaldi-trunk/tools/openfst-1.3.2/lib64/fst Can you do a ls -l of that directory? What did it install there? It seems to think it installed something. Dan On Wed, May 8, 2013 at 12:02 PM, Daniel Povey <dp...@gm...> wrote: > I could not figure out how to authorize the message, it rejected my > password. Please send it to dp...@gm... > Dan > > > > On Wed, May 8, 2013 at 11:42 AM, Mailing list used for User Communication > and Updates <kal...@li...> wrote: > >> >> >> On 05/08/2013 10:59 AM, Mailing list used for User Communication and >> Updates wrote: >> > Try doing "make" in the tools/ directory and redirect the output to a >> > file, e.g. make >& foo >> > and paste the file into the email, something seems to have gone wrong. >> > The symlinks should be automatically created and regardless you should >> > have an openfst.a file >> > Dan >> > >> > >> > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User >> > Communication and Updates <kal...@li... >> > <mailto:kal...@li...>> wrote: >> > >> > >> > >> > On 05/08/2013 10:34 AM, Mailing list used for User Communication and >> > Updates wrote: >> > > Actually, the problem might also be that the "make install" part >> > of the >> > > OpenFST installation failed, because there should be a file >> > > openfst-1.3.2/lib/openfst.a >> > > Type "make openfst_tgt" in the tools/ directory and see what >> happens >> > > Dan >> > > >> > > >> > > >> > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm... >> > <mailto:dp...@gm...> >> > > <mailto:dp...@gm... <mailto:dp...@gm...>>> wrote: >> > > >> > > There should be a soft link from "openfst" to >> > "openfst-1.3.2". See >> > > if it exists and try to figure out why not, if it does not. >> > > Dan >> > > >> > > >> > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User >> > > Communication and Updates <kal...@li... >> > <mailto:kal...@li...> >> > > <mailto:kal...@li... >> > <mailto:kal...@li...>>> wrote: >> > > >> > > >> > > >> > > On 05/08/2013 10:10 AM, Mailing list used for User >> > Communication and >> > > Updates wrote: >> > > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for >> User >> > > > Communication and Updates >> > <kal...@li... >> > <mailto:kal...@li...> >> > > <mailto:kal...@li... >> > <mailto:kal...@li...>>> wrote: >> > > >> Using Opensuse 12.3 64 bit, kernel 3.9. >> > > >> >> > > >> 1. I issued svn co >> > svn://svn.code.sf.net/p/kaldi/code/trunk >> > <http://svn.code.sf.net/p/kaldi/code/trunk> >> > > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk >> > > >> 2. download appeared to finish correctly >> > > >> 3. examined INSTALL, went into dir /tools and did >> make, >> > > finished without >> > > >> error as far as I can tell >> > > >> 4. then ../src and ./configure, which stops at >> > > >> >> > > >> $ ./configure >> > > >> Configuring ... >> > > >> Checking OpenFST library in >> > > /home/colin/kaldi-trunk/tools/openfst ... >> > > >> Checking OpenFst library was patched. >> > > >> Doing OS specific configurations ... >> > > >> ***configure failed: Static OpenFST library not >> > found: See >> > > >> ../tools/INSTALL *** >> > > > >> > > > Could you check to see if you have the following file >> > > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally >> > typing make >> > > in the >> > > > tools directory should create it, unless there was >> > some error >> > > that >> > > > didn't get reported. >> > > > >> > > >> > > $ find ./ -name libfst.a >> > > ./tools/openfst-1.3.2/lib64/libfst.a >> > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a >> > > >> > >> > "$ find ./ -name openfst.a" does not find anything. >> > >> > Did "make openfst_tgt" which completed successfully and created a >> bunch >> > of stuff. Repeated the two searches and no change to either. >> > >> > Will now try the symlink stuff. Thanks. >> > >> >> Dan, I did the re-make and it is on the way to the list. The complete >> reply was stopped by the bouncer waiting for mod since it thinks the >> message is too big. >> >> In short, still no openfst.a. Thanks. >> >> -- >> --- >> Colin Beckingham >> 613-454-5369 >> http://www.it4gh.com >> >> >> ------------------------------------------------------------------------------ >> Learn Graph Databases - Download FREE O'Reilly Book >> "Graph Databases" is the definitive new guide to graph databases and >> their applications. This 200-page book is written by three acclaimed >> leaders in the field. The early access version is available now. >> Download your free book today! http://p.sf.net/sfu/neotech_d2d_may >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 16:02:28
|
I could not figure out how to authorize the message, it rejected my password. Please send it to dp...@gm... Dan On Wed, May 8, 2013 at 11:42 AM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > > > On 05/08/2013 10:59 AM, Mailing list used for User Communication and > Updates wrote: > > Try doing "make" in the tools/ directory and redirect the output to a > > file, e.g. make >& foo > > and paste the file into the email, something seems to have gone wrong. > > The symlinks should be automatically created and regardless you should > > have an openfst.a file > > Dan > > > > > > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User > > Communication and Updates <kal...@li... > > <mailto:kal...@li...>> wrote: > > > > > > > > On 05/08/2013 10:34 AM, Mailing list used for User Communication and > > Updates wrote: > > > Actually, the problem might also be that the "make install" part > > of the > > > OpenFST installation failed, because there should be a file > > > openfst-1.3.2/lib/openfst.a > > > Type "make openfst_tgt" in the tools/ directory and see what > happens > > > Dan > > > > > > > > > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm... > > <mailto:dp...@gm...> > > > <mailto:dp...@gm... <mailto:dp...@gm...>>> wrote: > > > > > > There should be a soft link from "openfst" to > > "openfst-1.3.2". See > > > if it exists and try to figure out why not, if it does not. > > > Dan > > > > > > > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User > > > Communication and Updates <kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>>> wrote: > > > > > > > > > > > > On 05/08/2013 10:10 AM, Mailing list used for User > > Communication and > > > Updates wrote: > > > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for > User > > > > Communication and Updates > > <kal...@li... > > <mailto:kal...@li...> > > > <mailto:kal...@li... > > <mailto:kal...@li...>>> wrote: > > > >> Using Opensuse 12.3 64 bit, kernel 3.9. > > > >> > > > >> 1. I issued svn co > > svn://svn.code.sf.net/p/kaldi/code/trunk > > <http://svn.code.sf.net/p/kaldi/code/trunk> > > > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk > > > >> 2. download appeared to finish correctly > > > >> 3. examined INSTALL, went into dir /tools and did > make, > > > finished without > > > >> error as far as I can tell > > > >> 4. then ../src and ./configure, which stops at > > > >> > > > >> $ ./configure > > > >> Configuring ... > > > >> Checking OpenFST library in > > > /home/colin/kaldi-trunk/tools/openfst ... > > > >> Checking OpenFst library was patched. > > > >> Doing OS specific configurations ... > > > >> ***configure failed: Static OpenFST library not > > found: See > > > >> ../tools/INSTALL *** > > > > > > > > Could you check to see if you have the following file > > > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally > > typing make > > > in the > > > > tools directory should create it, unless there was > > some error > > > that > > > > didn't get reported. > > > > > > > > > > $ find ./ -name libfst.a > > > ./tools/openfst-1.3.2/lib64/libfst.a > > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > > > > > > "$ find ./ -name openfst.a" does not find anything. > > > > Did "make openfst_tgt" which completed successfully and created a > bunch > > of stuff. Repeated the two searches and no change to either. > > > > Will now try the symlink stuff. Thanks. > > > > Dan, I did the re-make and it is on the way to the list. The complete > reply was stopped by the bouncer waiting for mod since it thinks the > message is too big. > > In short, still no openfst.a. Thanks. > > -- > --- > Colin Beckingham > 613-454-5369 > http://www.it4gh.com > > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 15:41:52
|
On 05/08/2013 10:59 AM, Mailing list used for User Communication and Updates wrote: > Try doing "make" in the tools/ directory and redirect the output to a > file, e.g. make >& foo > and paste the file into the email, something seems to have gone wrong. > The symlinks should be automatically created and regardless you should > have an openfst.a file > Dan > > > On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User > Communication and Updates <kal...@li... > <mailto:kal...@li...>> wrote: > > > > On 05/08/2013 10:34 AM, Mailing list used for User Communication and > Updates wrote: > > Actually, the problem might also be that the "make install" part > of the > > OpenFST installation failed, because there should be a file > > openfst-1.3.2/lib/openfst.a > > Type "make openfst_tgt" in the tools/ directory and see what happens > > Dan > > > > > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm... > <mailto:dp...@gm...> > > <mailto:dp...@gm... <mailto:dp...@gm...>>> wrote: > > > > There should be a soft link from "openfst" to > "openfst-1.3.2". See > > if it exists and try to figure out why not, if it does not. > > Dan > > > > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User > > Communication and Updates <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>> wrote: > > > > > > > > On 05/08/2013 10:10 AM, Mailing list used for User > Communication and > > Updates wrote: > > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for User > > > Communication and Updates > <kal...@li... > <mailto:kal...@li...> > > <mailto:kal...@li... > <mailto:kal...@li...>>> wrote: > > >> Using Opensuse 12.3 64 bit, kernel 3.9. > > >> > > >> 1. I issued svn co > svn://svn.code.sf.net/p/kaldi/code/trunk > <http://svn.code.sf.net/p/kaldi/code/trunk> > > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk > > >> 2. download appeared to finish correctly > > >> 3. examined INSTALL, went into dir /tools and did make, > > finished without > > >> error as far as I can tell > > >> 4. then ../src and ./configure, which stops at > > >> > > >> $ ./configure > > >> Configuring ... > > >> Checking OpenFST library in > > /home/colin/kaldi-trunk/tools/openfst ... > > >> Checking OpenFst library was patched. > > >> Doing OS specific configurations ... > > >> ***configure failed: Static OpenFST library not > found: See > > >> ../tools/INSTALL *** > > > > > > Could you check to see if you have the following file > > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally > typing make > > in the > > > tools directory should create it, unless there was > some error > > that > > > didn't get reported. > > > > > > > $ find ./ -name libfst.a > > ./tools/openfst-1.3.2/lib64/libfst.a > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > > > "$ find ./ -name openfst.a" does not find anything. > > Did "make openfst_tgt" which completed successfully and created a bunch > of stuff. Repeated the two searches and no change to either. > > Will now try the symlink stuff. Thanks. > Dan, I did the re-make and it is on the way to the list. The complete reply was stopped by the bouncer waiting for mod since it thinks the message is too big. In short, still no openfst.a. Thanks. -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 15:05:47
|
On 05/08/2013 10:33 AM, Mailing list used for User Communication and Updates wrote: > On Wed, May 8, 2013 at 3:14 PM, Mailing list used for User > Communication and Updates <kal...@li...> wrote: > >>>> Using Opensuse 12.3 64 bit, kernel 3.9. > >>>> $ ./configure >>>> Configuring ... >>>> Checking OpenFST library in /home/colin/kaldi-trunk/tools/openfst ... >>>> Checking OpenFst library was patched. >>>> Doing OS specific configurations ... >>>> ***configure failed: Static OpenFST library not found: See >>>> ../tools/INSTALL *** >> >> $ find ./ -name libfst.a >> ./tools/openfst-1.3.2/lib64/libfst.a >> ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > OK, a simple fix will be to create a symlink for libfst.a in > openfst-1.3.2/lib. Also, tools/openfst-1.3.2 itself should be > symlinked as tools/openfst -- if not, let us know. But I am surprised > that the directory is lib64 an not lib. This could be an OS-specific > issue that I cannot recreate. > -Arnab > Created symlink for libfst.a. tools/openfst-1.3.2 is already symlinked to openfst Attempted new make in src, but still same error. Will now do record of make in tools dir per Dan. -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 14:59:07
|
Try doing "make" in the tools/ directory and redirect the output to a file, e.g. make >& foo and paste the file into the email, something seems to have gone wrong. The symlinks should be automatically created and regardless you should have an openfst.a file Dan On Wed, May 8, 2013 at 10:54 AM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > > > On 05/08/2013 10:34 AM, Mailing list used for User Communication and > Updates wrote: > > Actually, the problem might also be that the "make install" part of the > > OpenFST installation failed, because there should be a file > > openfst-1.3.2/lib/openfst.a > > Type "make openfst_tgt" in the tools/ directory and see what happens > > Dan > > > > > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm... > > <mailto:dp...@gm...>> wrote: > > > > There should be a soft link from "openfst" to "openfst-1.3.2". See > > if it exists and try to figure out why not, if it does not. > > Dan > > > > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User > > Communication and Updates <kal...@li... > > <mailto:kal...@li...>> wrote: > > > > > > > > On 05/08/2013 10:10 AM, Mailing list used for User Communication > and > > Updates wrote: > > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for User > > > Communication and Updates <kal...@li... > > <mailto:kal...@li...>> wrote: > > >> Using Opensuse 12.3 64 bit, kernel 3.9. > > >> > > >> 1. I issued svn co svn://svn.code.sf.net/p/kaldi/code/trunk > > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk > > >> 2. download appeared to finish correctly > > >> 3. examined INSTALL, went into dir /tools and did make, > > finished without > > >> error as far as I can tell > > >> 4. then ../src and ./configure, which stops at > > >> > > >> $ ./configure > > >> Configuring ... > > >> Checking OpenFST library in > > /home/colin/kaldi-trunk/tools/openfst ... > > >> Checking OpenFst library was patched. > > >> Doing OS specific configurations ... > > >> ***configure failed: Static OpenFST library not found: See > > >> ../tools/INSTALL *** > > > > > > Could you check to see if you have the following file > > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally typing make > > in the > > > tools directory should create it, unless there was some error > > that > > > didn't get reported. > > > > > > > $ find ./ -name libfst.a > > ./tools/openfst-1.3.2/lib64/libfst.a > > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > > > "$ find ./ -name openfst.a" does not find anything. > > Did "make openfst_tgt" which completed successfully and created a bunch > of stuff. Repeated the two searches and no change to either. > > Will now try the symlink stuff. Thanks. > > -- > --- > Colin Beckingham > 613-454-5369 > http://www.it4gh.com > > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 14:54:17
|
On 05/08/2013 10:34 AM, Mailing list used for User Communication and Updates wrote: > Actually, the problem might also be that the "make install" part of the > OpenFST installation failed, because there should be a file > openfst-1.3.2/lib/openfst.a > Type "make openfst_tgt" in the tools/ directory and see what happens > Dan > > > > On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm... > <mailto:dp...@gm...>> wrote: > > There should be a soft link from "openfst" to "openfst-1.3.2". See > if it exists and try to figure out why not, if it does not. > Dan > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User > Communication and Updates <kal...@li... > <mailto:kal...@li...>> wrote: > > > > On 05/08/2013 10:10 AM, Mailing list used for User Communication and > Updates wrote: > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for User > > Communication and Updates <kal...@li... > <mailto:kal...@li...>> wrote: > >> Using Opensuse 12.3 64 bit, kernel 3.9. > >> > >> 1. I issued svn co svn://svn.code.sf.net/p/kaldi/code/trunk > <http://svn.code.sf.net/p/kaldi/code/trunk> kaldi-trunk > >> 2. download appeared to finish correctly > >> 3. examined INSTALL, went into dir /tools and did make, > finished without > >> error as far as I can tell > >> 4. then ../src and ./configure, which stops at > >> > >> $ ./configure > >> Configuring ... > >> Checking OpenFST library in > /home/colin/kaldi-trunk/tools/openfst ... > >> Checking OpenFst library was patched. > >> Doing OS specific configurations ... > >> ***configure failed: Static OpenFST library not found: See > >> ../tools/INSTALL *** > > > > Could you check to see if you have the following file > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally typing make > in the > > tools directory should create it, unless there was some error > that > > didn't get reported. > > > > $ find ./ -name libfst.a > ./tools/openfst-1.3.2/lib64/libfst.a > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > "$ find ./ -name openfst.a" does not find anything. Did "make openfst_tgt" which completed successfully and created a bunch of stuff. Repeated the two searches and no change to either. Will now try the symlink stuff. Thanks. -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 14:34:44
|
Actually, the problem might also be that the "make install" part of the OpenFST installation failed, because there should be a file openfst-1.3.2/lib/openfst.a Type "make openfst_tgt" in the tools/ directory and see what happens Dan On Wed, May 8, 2013 at 10:30 AM, Daniel Povey <dp...@gm...> wrote: > There should be a soft link from "openfst" to "openfst-1.3.2". See if it > exists and try to figure out why not, if it does not. > Dan > > > On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User Communication > and Updates <kal...@li...> wrote: > >> >> >> On 05/08/2013 10:10 AM, Mailing list used for User Communication and >> Updates wrote: >> > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for User >> > Communication and Updates <kal...@li...> wrote: >> >> Using Opensuse 12.3 64 bit, kernel 3.9. >> >> >> >> 1. I issued svn co svn://svn.code.sf.net/p/kaldi/code/trunkkaldi-trunk >> >> 2. download appeared to finish correctly >> >> 3. examined INSTALL, went into dir /tools and did make, finished >> without >> >> error as far as I can tell >> >> 4. then ../src and ./configure, which stops at >> >> >> >> $ ./configure >> >> Configuring ... >> >> Checking OpenFST library in /home/colin/kaldi-trunk/tools/openfst ... >> >> Checking OpenFst library was patched. >> >> Doing OS specific configurations ... >> >> ***configure failed: Static OpenFST library not found: See >> >> ../tools/INSTALL *** >> > >> > Could you check to see if you have the following file >> > kaldi-trunk/tools/openfst/lib/libfst.a? Normally typing make in the >> > tools directory should create it, unless there was some error that >> > didn't get reported. >> > >> >> $ find ./ -name libfst.a >> ./tools/openfst-1.3.2/lib64/libfst.a >> ./tools/openfst-1.3.2/src/lib/.libs/libfst.a >> >> -- >> --- >> Colin Beckingham >> 613-454-5369 >> http://www.it4gh.com >> >> >> ------------------------------------------------------------------------------ >> Learn Graph Databases - Download FREE O'Reilly Book >> "Graph Databases" is the definitive new guide to graph databases and >> their applications. This 200-page book is written by three acclaimed >> leaders in the field. The early access version is available now. >> Download your free book today! http://p.sf.net/sfu/neotech_d2d_may >> _______________________________________________ >> Kaldi-users mailing list >> Kal...@li... >> https://lists.sourceforge.net/lists/listinfo/kaldi-users >> > > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 14:33:55
|
On Wed, May 8, 2013 at 3:14 PM, Mailing list used for User Communication and Updates <kal...@li...> wrote: >>> Using Opensuse 12.3 64 bit, kernel 3.9. >>> $ ./configure >>> Configuring ... >>> Checking OpenFST library in /home/colin/kaldi-trunk/tools/openfst ... >>> Checking OpenFst library was patched. >>> Doing OS specific configurations ... >>> ***configure failed: Static OpenFST library not found: See >>> ../tools/INSTALL *** > > $ find ./ -name libfst.a > ./tools/openfst-1.3.2/lib64/libfst.a > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a OK, a simple fix will be to create a symlink for libfst.a in openfst-1.3.2/lib. Also, tools/openfst-1.3.2 itself should be symlinked as tools/openfst -- if not, let us know. But I am surprised that the directory is lib64 an not lib. This could be an OS-specific issue that I cannot recreate. -Arnab |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 14:30:55
|
There should be a soft link from "openfst" to "openfst-1.3.2". See if it exists and try to figure out why not, if it does not. Dan On Wed, May 8, 2013 at 10:14 AM, Mailing list used for User Communication and Updates <kal...@li...> wrote: > > > On 05/08/2013 10:10 AM, Mailing list used for User Communication and > Updates wrote: > > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for User > > Communication and Updates <kal...@li...> wrote: > >> Using Opensuse 12.3 64 bit, kernel 3.9. > >> > >> 1. I issued svn co svn://svn.code.sf.net/p/kaldi/code/trunk kaldi-trunk > >> 2. download appeared to finish correctly > >> 3. examined INSTALL, went into dir /tools and did make, finished without > >> error as far as I can tell > >> 4. then ../src and ./configure, which stops at > >> > >> $ ./configure > >> Configuring ... > >> Checking OpenFST library in /home/colin/kaldi-trunk/tools/openfst ... > >> Checking OpenFst library was patched. > >> Doing OS specific configurations ... > >> ***configure failed: Static OpenFST library not found: See > >> ../tools/INSTALL *** > > > > Could you check to see if you have the following file > > kaldi-trunk/tools/openfst/lib/libfst.a? Normally typing make in the > > tools directory should create it, unless there was some error that > > didn't get reported. > > > > $ find ./ -name libfst.a > ./tools/openfst-1.3.2/lib64/libfst.a > ./tools/openfst-1.3.2/src/lib/.libs/libfst.a > > -- > --- > Colin Beckingham > 613-454-5369 > http://www.it4gh.com > > > ------------------------------------------------------------------------------ > Learn Graph Databases - Download FREE O'Reilly Book > "Graph Databases" is the definitive new guide to graph databases and > their applications. This 200-page book is written by three acclaimed > leaders in the field. The early access version is available now. > Download your free book today! http://p.sf.net/sfu/neotech_d2d_may > _______________________________________________ > Kaldi-users mailing list > Kal...@li... > https://lists.sourceforge.net/lists/listinfo/kaldi-users > |
|
From: Mailing l. u. f. U. C. a. U. <kal...@li...> - 2013-05-08 14:14:30
|
On 05/08/2013 10:10 AM, Mailing list used for User Communication and Updates wrote: > On Wed, May 8, 2013 at 2:52 PM, Mailing list used for User > Communication and Updates <kal...@li...> wrote: >> Using Opensuse 12.3 64 bit, kernel 3.9. >> >> 1. I issued svn co svn://svn.code.sf.net/p/kaldi/code/trunk kaldi-trunk >> 2. download appeared to finish correctly >> 3. examined INSTALL, went into dir /tools and did make, finished without >> error as far as I can tell >> 4. then ../src and ./configure, which stops at >> >> $ ./configure >> Configuring ... >> Checking OpenFST library in /home/colin/kaldi-trunk/tools/openfst ... >> Checking OpenFst library was patched. >> Doing OS specific configurations ... >> ***configure failed: Static OpenFST library not found: See >> ../tools/INSTALL *** > > Could you check to see if you have the following file > kaldi-trunk/tools/openfst/lib/libfst.a? Normally typing make in the > tools directory should create it, unless there was some error that > didn't get reported. > $ find ./ -name libfst.a ./tools/openfst-1.3.2/lib64/libfst.a ./tools/openfst-1.3.2/src/lib/.libs/libfst.a -- --- Colin Beckingham 613-454-5369 http://www.it4gh.com |
1 message has been excluded from this view by a project administrator.