kaldi-developers — Kaldi Developers

Re: [Kaldi-developers] Memory grows when running latgen-faster-mapped

[Li P. <lip...@gm...>]

Thanks, Dan. I did run 1000 utterances, and when the program terminated,
valgrind reports no direct memory leak.
在 2013年8月28日 下午9:34，"Daniel Povey" <dp...@gm...>写道：

> Valgrind will also not report memory leaks till the program ends.  You
> might have to run with just one or two utterances to let it terminate.
> Dan
>
>
> On Wed, Aug 28, 2013 at 3:32 PM, Arnab Ghoshal <ar...@gm...> wrote:
> > It is possible for the lattice generation to take a lot of memory.
> > Have you tried changing the --max-mem, --lattice-beam, --beam options
> > to see if it runs properly? Also, does this happen for a particular
> > utterance or all utterances?
> > -Arnab
> >
> > On Wed, Aug 28, 2013 at 7:22 AM, Li Peng <lip...@gm...> wrote:
> >> Hi,
> >>
> >> When I used latgen-faster-mapped with DNN model to generate lattices, I
> >> observed that the memory usage keeps growing and exhausts the system's
> >> memory at last. I tried to use valgrind to find if there's a memory
> leak,
> >> but got no clues. So I write to report this problem, but I'm not sure if
> >> there is a bug or it is just my own case.
> >>
> >> Best regards,
> >>
> >> Li Peng
> >>
> >>
> ------------------------------------------------------------------------------
> >> Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
> >> Discover the easy way to master current and previous Microsoft
> technologies
> >> and advance your career. Get an incredible 1,500+ hours of step-by-step
> >> tutorial videos with LearnDevNow. Subscribe today and save!
> >>
> http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
> >> _______________________________________________
> >> Kaldi-developers mailing list
> >> Kal...@li...
> >> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
> >>
> >
> >
> ------------------------------------------------------------------------------
> > Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
> > Discover the easy way to master current and previous Microsoft
> technologies
> > and advance your career. Get an incredible 1,500+ hours of step-by-step
> > tutorial videos with LearnDevNow. Subscribe today and save!
> >
> http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
> > _______________________________________________
> > Kaldi-developers mailing list
> > Kal...@li...
> > https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>

Re: [Kaldi-developers] Memory grows when running latgen-faster-mapped

[Li P. <lip...@gm...>]

Sorry for that I don't know the details of how the program works, so I'm
not sure how to tune the options properly.

The memory consumption grows little by little as the number of processed
utterances increases. When the program runs for one day, it grows from the
starting 100MB to several GB.
在 2013年8月28日 下午9:33，"Arnab Ghoshal" <ar...@gm...>写道：

> It is possible for the lattice generation to take a lot of memory.
> Have you tried changing the --max-mem, --lattice-beam, --beam options
> to see if it runs properly? Also, does this happen for a particular
> utterance or all utterances?
> -Arnab
>
> On Wed, Aug 28, 2013 at 7:22 AM, Li Peng <lip...@gm...> wrote:
> > Hi,
> >
> > When I used latgen-faster-mapped with DNN model to generate lattices, I
> > observed that the memory usage keeps growing and exhausts the system's
> > memory at last. I tried to use valgrind to find if there's a memory leak,
> > but got no clues. So I write to report this problem, but I'm not sure if
> > there is a bug or it is just my own case.
> >
> > Best regards,
> >
> > Li Peng
> >
> >
> ------------------------------------------------------------------------------
> > Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
> > Discover the easy way to master current and previous Microsoft
> technologies
> > and advance your career. Get an incredible 1,500+ hours of step-by-step
> > tutorial videos with LearnDevNow. Subscribe today and save!
> >
> http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
> > _______________________________________________
> > Kaldi-developers mailing list
> > Kal...@li...
> > https://lists.sourceforge.net/lists/listinfo/kaldi-developers
> >
>

Re: [Kaldi-developers] Memory grows when running latgen-faster-mapped

[Daniel P. <dp...@gm...>]

Valgrind will also not report memory leaks till the program ends.  You
might have to run with just one or two utterances to let it terminate.
Dan


On Wed, Aug 28, 2013 at 3:32 PM, Arnab Ghoshal <ar...@gm...> wrote:
> It is possible for the lattice generation to take a lot of memory.
> Have you tried changing the --max-mem, --lattice-beam, --beam options
> to see if it runs properly? Also, does this happen for a particular
> utterance or all utterances?
> -Arnab
>
> On Wed, Aug 28, 2013 at 7:22 AM, Li Peng <lip...@gm...> wrote:
>> Hi,
>>
>> When I used latgen-faster-mapped with DNN model to generate lattices, I
>> observed that the memory usage keeps growing and exhausts the system's
>> memory at last. I tried to use valgrind to find if there's a memory leak,
>> but got no clues. So I write to report this problem, but I'm not sure if
>> there is a bug or it is just my own case.
>>
>> Best regards,
>>
>> Li Peng
>>
>> ------------------------------------------------------------------------------
>> Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
>> Discover the easy way to master current and previous Microsoft technologies
>> and advance your career. Get an incredible 1,500+ hours of step-by-step
>> tutorial videos with LearnDevNow. Subscribe today and save!
>> http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
>> _______________________________________________
>> Kaldi-developers mailing list
>> Kal...@li...
>> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>>
>
> ------------------------------------------------------------------------------
> Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
> Discover the easy way to master current and previous Microsoft technologies
> and advance your career. Get an incredible 1,500+ hours of step-by-step
> tutorial videos with LearnDevNow. Subscribe today and save!
> http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

Re: [Kaldi-developers] Memory grows when running latgen-faster-mapped

[Arnab G. <ar...@gm...>]

It is possible for the lattice generation to take a lot of memory.
Have you tried changing the --max-mem, --lattice-beam, --beam options
to see if it runs properly? Also, does this happen for a particular
utterance or all utterances?
-Arnab

On Wed, Aug 28, 2013 at 7:22 AM, Li Peng <lip...@gm...> wrote:
> Hi,
>
> When I used latgen-faster-mapped with DNN model to generate lattices, I
> observed that the memory usage keeps growing and exhausts the system's
> memory at last. I tried to use valgrind to find if there's a memory leak,
> but got no clues. So I write to report this problem, but I'm not sure if
> there is a bug or it is just my own case.
>
> Best regards,
>
> Li Peng
>
> ------------------------------------------------------------------------------
> Learn the latest--Visual Studio 2012, SharePoint 2013, SQL 2012, more!
> Discover the easy way to master current and previous Microsoft technologies
> and advance your career. Get an incredible 1,500+ hours of step-by-step
> tutorial videos with LearnDevNow. Subscribe today and save!
> http://pubads.g.doubleclick.net/gampad/clk?id=58040911&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>

[Kaldi-developers] Memory grows when running latgen-faster-mapped

[Li P. <lip...@gm...>]

Hi,

When I used latgen-faster-mapped with DNN model to generate lattices, I
observed that the memory usage keeps growing and exhausts the system's
memory at last. I tried to use valgrind to find if there's a memory leak,
but got no clues. So I write to report this problem, but I'm not sure if
there is a bug or it is just my own case.

Best regards,

Li Peng

Re: [Kaldi-developers] How to redo recognition on new lattice

[Daniel P. <dp...@gm...>]

Actually, Arnab, it looks like gmm-decode-faster has already been
modified so it can read an archives of FSTs.
Anna-- you can also look at the script steps/decode_fromlats.sh
Dan


On Fri, Aug 23, 2013 at 1:15 PM, Arnab Ghoshal <ar...@gm...> wrote:
> Anna- if I understand correctly, you have made some modification to
> the HCLG.fst and have separate decoding graphs for each utterance. In
> that case you could simply call gmm-latgen-faster for each utterance:
> you may have to use latbin/lattice-to-fst to convert the lattice to a
> word graph and use a single line of the feats.scp as input. The other
> option will be to write a specialized form of gmm-latgen-faster that
> takes separate decoding graphs for each utterances (as an archive or
> scp). You can see an example of such an approach in
> bin/compile-train-graphs-fsts (compare to bin/compile-train-graphs).
> -Arnab
>
>
> On Sun, Aug 18, 2013 at 1:31 PM, Anna Schmidt
> <an...@co...> wrote:
>> Dear Kaldi developers,
>>
>> I am trying to combine Kaldi recognition results (in form of the result
>> lattice that is output when decoding with gmm-latgen-faster) with
>> situation dependent world knowledge which can also be represented as a
>> lattice. For this I implemented a 'merging' of two lattices to produce a
>> combined structure that is a lot smaller than HCLG, but should still
>> contain the correct recognition hypothesis for the current sound file.
>> We would like to redo the recognition on this structures to reduce WER
>> further.
>>
>> So, my question is:
>> Using Kaldi, how would it be possible to rerun the recognition on this
>> new, combined lattice? There exists one unique combined lattice for each
>> wav file in our test corpus since the situational knowledge is different
>> for every file.
>>
>> Thank you very much for your help and all the best,
>>
>> Anna Schmidt
>>
>> ------------------------------------------------------------------------------
>> Introducing Performance Central, a new site from SourceForge and
>> AppDynamics. Performance Central is your source for news, insights,
>> analysis and resources for efficient Application Performance Management.
>> Visit us today!
>> http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
>> _______________________________________________
>> Kaldi-developers mailing list
>> Kal...@li...
>> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>
> ------------------------------------------------------------------------------
> Introducing Performance Central, a new site from SourceForge and
> AppDynamics. Performance Central is your source for news, insights,
> analysis and resources for efficient Application Performance Management.
> Visit us today!
> http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

Re: [Kaldi-developers] How to redo recognition on new lattice

[Arnab G. <ar...@gm...>]

Anna- if I understand correctly, you have made some modification to
the HCLG.fst and have separate decoding graphs for each utterance. In
that case you could simply call gmm-latgen-faster for each utterance:
you may have to use latbin/lattice-to-fst to convert the lattice to a
word graph and use a single line of the feats.scp as input. The other
option will be to write a specialized form of gmm-latgen-faster that
takes separate decoding graphs for each utterances (as an archive or
scp). You can see an example of such an approach in
bin/compile-train-graphs-fsts (compare to bin/compile-train-graphs).
-Arnab


On Sun, Aug 18, 2013 at 1:31 PM, Anna Schmidt
<an...@co...> wrote:
> Dear Kaldi developers,
>
> I am trying to combine Kaldi recognition results (in form of the result
> lattice that is output when decoding with gmm-latgen-faster) with
> situation dependent world knowledge which can also be represented as a
> lattice. For this I implemented a 'merging' of two lattices to produce a
> combined structure that is a lot smaller than HCLG, but should still
> contain the correct recognition hypothesis for the current sound file.
> We would like to redo the recognition on this structures to reduce WER
> further.
>
> So, my question is:
> Using Kaldi, how would it be possible to rerun the recognition on this
> new, combined lattice? There exists one unique combined lattice for each
> wav file in our test corpus since the situational knowledge is different
> for every file.
>
> Thank you very much for your help and all the best,
>
> Anna Schmidt
>
> ------------------------------------------------------------------------------
> Introducing Performance Central, a new site from SourceForge and
> AppDynamics. Performance Central is your source for news, insights,
> analysis and resources for efficient Application Performance Management.
> Visit us today!
> http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

Re: [Kaldi-developers] First time user :) script bug in wsj/s1 re: CMU dictionary

[Arnab G. <ar...@gm...>]

Eric- it's fixed in the s5 recipe. s1-s4 recipes are deprecated. -Arnab

On Thu, Aug 22, 2013 at 6:37 PM, Eric Riebling <er...@cs...> wrote:
> First step in the wsj/s1 recipe script requests a dictionary from CMU
> sphinx, but that dictionary has moved; perhaps the script can be updated
> accordingly (and others like it)
>
> SCRIPT TEXT:
>
> # (1) To get the CMU dictionary, do:
> svn co https://cmusphinx.svn.sourceforge.net/svnroot/cmusphinx/trunk/cmudict/
> # got this at revision 10966 in the last tests done before releasing v1.0.
> # can add -r 10966 for strict compatibility.
>
> ERROR:
>
> svn: Repository moved permanently to 'https://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict'; please relocate
>
> --
> Eric Riebling                 Senior Research Programmer
> http://ericriebling.com       CMU Language Technologies Institute
> 412-268-9872                  GHC 6713
>
>
> ------------------------------------------------------------------------------
> Introducing Performance Central, a new site from SourceForge and
> AppDynamics. Performance Central is your source for news, insights,
> analysis and resources for efficient Application Performance Management.
> Visit us today!
> http://pubads.g.doubleclick.net/gampad/clk?id=48897511&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

[Kaldi-developers] First time user :) script bug in wsj/s1 re: CMU dictionary

[Eric R. <er...@cs...>]

First step in the wsj/s1 recipe script requests a dictionary from CMU
sphinx, but that dictionary has moved; perhaps the script can be updated
accordingly (and others like it)

SCRIPT TEXT:

# (1) To get the CMU dictionary, do:
svn co https://cmusphinx.svn.sourceforge.net/svnroot/cmusphinx/trunk/cmudict/
# got this at revision 10966 in the last tests done before releasing v1.0.
# can add -r 10966 for strict compatibility.

ERROR:

svn: Repository moved permanently to 'https://svn.code.sf.net/p/cmusphinx/code/trunk/cmudict'; please relocate

-- 
Eric Riebling                 Senior Research Programmer
http://ericriebling.com       CMU Language Technologies Institute
412-268-9872                  GHC 6713
      

[Kaldi-developers] How to redo recognition on new lattice

[Anna S. <an...@co...>]

Dear Kaldi developers,

I am trying to combine Kaldi recognition results (in form of the result 
lattice that is output when decoding with gmm-latgen-faster) with 
situation dependent world knowledge which can also be represented as a 
lattice. For this I implemented a 'merging' of two lattices to produce a 
combined structure that is a lot smaller than HCLG, but should still 
contain the correct recognition hypothesis for the current sound file.
We would like to redo the recognition on this structures to reduce WER 
further.

So, my question is:
Using Kaldi, how would it be possible to rerun the recognition on this 
new, combined lattice? There exists one unique combined lattice for each 
wav file in our test corpus since the situational knowledge is different 
for every file.

Thank you very much for your help and all the best,

Anna Schmidt

Re: [Kaldi-developers] Adapting AM to specific data

[Daniel P. <dp...@gm...>]

The simplest and generally best method of adaptation is to do
Constrained MLLR a.k.a. fMLLR in test time.  If you are using the
decode_fmllr.sh script it already does this.  Basically it computes a
linear transform of the features for each speaker.  We may also have a
script somewhere for MAP adaptation but I don't recall what it would
be called.  That might give additional gains if you MAP adapted to the
ATIS-specific data.
Dan


On Fri, Aug 16, 2013 at 9:39 AM, Arif Khan <ife...@gm...> wrote:
> Dear All,
>
> I want to train an acoustic model for the Air traffic commands (ATC). As we
> don't have enough training data for the ATC, so I combined the WSJ0 and
> TIDIGITS, to have good estimation.
>
> But still the WER has not improved, because the test data is not from native
> speaker of English.
>
> 1) What mechanism we can use to adopt the AM model to the test data.
> (Considering that I have some data for this.) like MAP or so.
>
> 2) Which module of KALDI is used for this.
>
> Any example or reference will be appreciated.
>
>
> Thanks in advance,
> Arif
>
> ------------------------------------------------------------------------------
> Get 100% visibility into Java/.NET code with AppDynamics Lite!
> It's a free troubleshooting tool designed for production.
> Get down to code-level detail for bottlenecks, with <2% overhead.
> Download for free and get started troubleshooting in minutes.
> http://pubads.g.doubleclick.net/gampad/clk?id=48897031&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>

[Kaldi-developers] Adapting AM to specific data

[Arif K. <ife...@gm...>]

Dear All,

I want to train an acoustic model for the Air traffic commands (ATC). As we
don't have enough training data for the ATC, so I combined the WSJ0 and
TIDIGITS, to have good estimation.

But still the WER has not improved, because the test data is not from
native speaker of English.

1) What mechanism we can use to adopt the AM model to the test data.
(Considering that I have some data for this.) like MAP or so.

2) Which module of KALDI is used for this.

Any example or reference will be appreciated.


Thanks in advance,
Arif

[Kaldi-developers] [Jenkins] Kaldi automatic build and test

[<jen...@a2...>]

Kaldi - Build # 83 - Failure:

Check console output at http://jenkins.a2ialab.com/jenkins/job/Kaldi/83/ to view the results.

Re: [Kaldi-developers] Please add scripts for checking input data

[Bo T. <dx...@16...>]

Thank you!
I'm sorry for not checking the existing scripts but KALDI is too powerful to work through :)

于 8/5/13 1:19 AM, Daniel Povey 写道:

You may also try the script utils/fix_data_dir.sh which automatically
fixes issues like sorting, IIRC.
Dan


On Sun, Aug 4, 2013 at 1:16 PM, Daniel Povey <dp...@gm...> wrote:

This has been recently added-- you are using the trunk, right?  It's
utils/validate_data_dir.sh
Dan


On Fri, Aug 2, 2013 at 8:14 AM, Bo Tian <dx...@16...> wrote:

Hello everyone,

I love KALDI very much for its variety of abilities to build models and
decode.

But could you please add an script to check the format of the input data
for training?

Today I tried to build acoustic model using my own data, I found it kept
failing because of unsorted text(spk2utt, etc.), and I sorted them
myself but it didn't work. Finally, I found it was advised to append
speaker id to utterance id for sorting.

Such problem is not difficult to solve, but it's difficult to check if
it's solved. Because I need to extract feat again and again(maybe it's
not needed but I don't know), and after run train_mon.sh for a while, it
tells me the error. It takes too tong. I think all these could be done
after I finish preparing the data before training phase.

I will appreciate your help!

Sincerely

--
Department of Computer Science and Technology, Tsinghua University
Bo Tian



------------------------------------------------------------------------------
Get your SQL database under version control now!
Version control is standard for application code, but databases havent
caught up. So what steps can you take to put your SQL databases under
version control? Why should you start doing it? Read more to find out.
http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
_______________________________________________
Kaldi-developers mailing list
Kal...@li...https://lists.sourceforge.net/lists/listinfo/kaldi-developers



-- 
Department of Computer Science and Technology, Tsinghua University
Bo Tian

Re: [Kaldi-developers] Please add scripts for checking input data

[Jan T. <af...@ce...>]

Hi, the wsj/s5 script utils/fix_data_dir.sh should be able to take care of
these things.
Yenda

> On Aug 2, 2013 8:14 AM, "Bo Tian" <dx...@16...> wrote:
>>
>> Hello everyone,
>>
>> I love KALDI very much for its variety of abilities to build models and
>> decode.
>>
>> But could you please add an script to check the format of the input data
>> for training?
>>
>> Today I tried to build acoustic model using my own data, I found it kept
>> failing because of unsorted text(spk2utt, etc.), and I sorted them
>> myself but it didn't work. Finally, I found it was advised to append
>> speaker id to utterance id for sorting.
>>
>> Such problem is not difficult to solve, but it's difficult to check if
>> it's solved. Because I need to extract feat again and again(maybe it's
>> not needed but I don't know), and after run train_mon.sh for a while, it
>> tells me the error. It takes too tong. I think all these could be done
>> after I finish preparing the data before training phase.
>>
>> I will appreciate your help!
>>
>> Sincerely
>>
>> --
>> Department of Computer Science and Technology, Tsinghua University
>> Bo Tian
>>
>>
>>
>>
------------------------------------------------------------------------------
>> Get your SQL database under version control now!
>> Version control is standard for application code, but databases havent
>> caught up. So what steps can you take to put your SQL databases under
>> version control? Why should you start doing it? Read more to find out.
>>
http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
>> _______________________________________________
>> Kaldi-developers mailing list
>> Kal...@li...
>> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

Re: [Kaldi-developers] Please add scripts for checking input data

[Daniel P. <dp...@gm...>]

You may also try the script utils/fix_data_dir.sh which automatically
fixes issues like sorting, IIRC.
Dan


On Sun, Aug 4, 2013 at 1:16 PM, Daniel Povey <dp...@gm...> wrote:
> This has been recently added-- you are using the trunk, right?  It's
> utils/validate_data_dir.sh
> Dan
>
>
> On Fri, Aug 2, 2013 at 8:14 AM, Bo Tian <dx...@16...> wrote:
>> Hello everyone,
>>
>> I love KALDI very much for its variety of abilities to build models and
>> decode.
>>
>> But could you please add an script to check the format of the input data
>> for training?
>>
>> Today I tried to build acoustic model using my own data, I found it kept
>> failing because of unsorted text(spk2utt, etc.), and I sorted them
>> myself but it didn't work. Finally, I found it was advised to append
>> speaker id to utterance id for sorting.
>>
>> Such problem is not difficult to solve, but it's difficult to check if
>> it's solved. Because I need to extract feat again and again(maybe it's
>> not needed but I don't know), and after run train_mon.sh for a while, it
>> tells me the error. It takes too tong. I think all these could be done
>> after I finish preparing the data before training phase.
>>
>> I will appreciate your help!
>>
>> Sincerely
>>
>> --
>> Department of Computer Science and Technology, Tsinghua University
>> Bo Tian
>>
>>
>>
>> ------------------------------------------------------------------------------
>> Get your SQL database under version control now!
>> Version control is standard for application code, but databases havent
>> caught up. So what steps can you take to put your SQL databases under
>> version control? Why should you start doing it? Read more to find out.
>> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
>> _______________________________________________
>> Kaldi-developers mailing list
>> Kal...@li...
>> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

Re: [Kaldi-developers] Please add scripts for checking input data

[Daniel P. <dp...@gm...>]

This has been recently added-- you are using the trunk, right?  It's
utils/validate_data_dir.sh
Dan


On Fri, Aug 2, 2013 at 8:14 AM, Bo Tian <dx...@16...> wrote:
> Hello everyone,
>
> I love KALDI very much for its variety of abilities to build models and
> decode.
>
> But could you please add an script to check the format of the input data
> for training?
>
> Today I tried to build acoustic model using my own data, I found it kept
> failing because of unsorted text(spk2utt, etc.), and I sorted them
> myself but it didn't work. Finally, I found it was advised to append
> speaker id to utterance id for sorting.
>
> Such problem is not difficult to solve, but it's difficult to check if
> it's solved. Because I need to extract feat again and again(maybe it's
> not needed but I don't know), and after run train_mon.sh for a while, it
> tells me the error. It takes too tong. I think all these could be done
> after I finish preparing the data before training phase.
>
> I will appreciate your help!
>
> Sincerely
>
> --
> Department of Computer Science and Technology, Tsinghua University
> Bo Tian
>
>
>
> ------------------------------------------------------------------------------
> Get your SQL database under version control now!
> Version control is standard for application code, but databases havent
> caught up. So what steps can you take to put your SQL databases under
> version control? Why should you start doing it? Read more to find out.
> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

[Kaldi-developers] Please add scripts for checking input data

[Bo T. <dx...@16...>]

Hello everyone,

I love KALDI very much for its variety of abilities to build models and
decode.

But could you please add an script to check the format of the input data
for training?

Today I tried to build acoustic model using my own data, I found it kept
failing because of unsorted text(spk2utt, etc.), and I sorted them
myself but it didn't work. Finally, I found it was advised to append
speaker id to utterance id for sorting.

Such problem is not difficult to solve, but it's difficult to check if
it's solved. Because I need to extract feat again and again(maybe it's
not needed but I don't know), and after run train_mon.sh for a while, it
tells me the error. It takes too tong. I think all these could be done
after I finish preparing the data before training phase.

I will appreciate your help!

Sincerely

-- 
Department of Computer Science and Technology, Tsinghua University
Bo Tian

Re: [Kaldi-developers] Problems in installing Kaldi

[Daniel P. <dp...@gm...>]

It's good that you told us.  The tutorial page seems to be out of
date, it refers to the old Sourceforge location.  I am updating the
website right now.
The command to check out the current version is
    svn co svn://svn.code.sf.net/p/kaldi/code/trunk kaldi-trunk

Dan


On Wed, Jul 31, 2013 at 12:43 PM, Ji He <jv...@uw...> wrote:
> Thanks for your reply. We have BLAS, CBLAS and CLAPACK installed by root
> admin. Let me check if these packages will be enough to build it, and how to
> set the dependency. One easy solution would be compile Kaldi on my laptop,
> but I prefer lab's machine so that other people can refer to it later.
>
> I looked at the Kaldi tutorial here:
> http://kaldi.sourceforge.net/tutorial_setup.html
> and instead of checking out version 1 code I checked out the trunk, i.e. svn
> co https://kaldi.svn.sourceforge.net/svnroot/kaldi/trunk kaldi-trunk
>
> Please let me know if there is a later version. Thanks.
>
>
> On Wed, Jul 31, 2013 at 9:13 AM, Daniel Povey <dp...@gm...> wrote:
>>
>> Where did you get the instructions to download Kaldi?  I'm concerned
>> that people are still getting out-of-date instructions with the "old"
>> sourceforge location.
>> Dan
>>
>>
>> On Wed, Jul 31, 2013 at 8:26 AM, Arnab Ghoshal <ar...@gm...> wrote:
>> > Kaldi needs some kind of linear algebra library. ATLAS is easily
>> > obtained. Otherwise if your system has MKL, you could use that as
>> > well. Check to see what messages install_atlas.sh generated (btw, you
>> > are using an older version, since the install_atlas.sh has now moved
>> > to tools/extras). The most common problem is that CPU throttling needs
>> > to be disabled for installing ATLAS, but that requires root access. It
>> > may be best to consult with your admin about ATLAS/MKL and to install
>> > one if none is present.
>> > -Arnab
>> >
>> > On Mon, Jul 29, 2013 at 1:35 AM, Ji He <jv...@uw...> wrote:
>> >> Hi there,
>> >>
>> >> I heard that Kaldi is becoming popular these days and I want to try it
>> >> myself. But I don't have access to root directory in my lab's machine,
>> >> so I
>> >> try to install it on my local space (and setting file dependencies
>> >> etc.). I
>> >> am not sure how to do this.
>> >>
>> >> Basically when I ran the normal installation steps, I got errors in
>> >> ./configure (in src/), it says:
>> >>
>> >> On Linux: Checking for linear algebra header files ...
>> >> Using ATLAS as the linear algebra library.
>> >> Could not find libatlas.a in any of the obvious places... will try
>> >> dynamic
>> >> libraries.
>> >> No libatlas.so in /usr/lib
>> >> No libatlas.so in /usr/lib/atlas
>> >> No libatlas.so in /usr/lib/atlas-sse2
>> >> No libatlas.so in /usr/lib/atlas-sse3
>> >> No libatlas.so in /usr/lib64
>> >> No libatlas.so in /usr/lib64/atlas
>> >> No libatlas.so in /usr/lib64/atlas-sse2
>> >> No libatlas.so in /usr/lib64/atlas-sse3
>> >> No libatlas.so in /usr/local/lib
>> >> No libatlas.so in /usr/local/lib/atlas
>> >> No libatlas.so in /usr/local/lib/atlas-sse2
>> >> No libatlas.so in /usr/local/lib/atlas-sse3
>> >> No libatlas.so in /usr/local/lib64
>> >> No libatlas.so in /usr/local/lib64/atlas
>> >> No libatlas.so in /usr/local/lib64/atlas-sse2
>> >> No libatlas.so in /usr/local/lib64/atlas-sse3
>> >> No libatlas.so in
>> >> /s1/jvking/temp/Kaldi/kaldi-trunk/src/../tools/ATLAS/build/install/lib/
>> >> No libatlas.so in /s1/jvking/temp/Kaldi/kaldi-trunk/tools/ATLAS/lib
>> >> Could not find libatlas.so in any of the obvious places.
>> >> ** Failed to configure ATLAS lbiraries ***
>> >> **  ERROR   **
>> >> **Configure cannot proceed automatically, but by editing kaldi.mk
>> >> ** you may be able to proceed (replace [somewhere] with a directory),
>> >> ** or install the ATLAS package on your machine,
>> >> ** or try going to ../tools and running install_atlas.sh, and running
>> >> ** this script (configure) again.
>> >>
>> >> I read how Kaldi is compiled and it seems I may need to edit the
>> >>
>> >> ATLASINC = [somewhere]/include
>> >> ATLASLIBS = [somewhere]/liblapack.a [somewhere]/libcblas.a
>> >> [somewhere]/libatlas.a [somewhere]/libf77blas.a
>> >>
>> >> lines in src/kaldi.mk, but I don't know where I should pointed it to. I
>> >> also
>> >> tried running ./tools/install_atlas.sh but have no idea what I should
>> >> do
>> >> after that step. I cannot find libatlas.a anywhere in my local
>> >> directory,
>> >> i.e. kaldi-trunk. I look forward to your quick reply.
>> >>
>> >> With regards,
>> >> HE Ji
>> >>
>> >>
>> >> ------------------------------------------------------------------------------
>> >> Get your SQL database under version control now!
>> >> Version control is standard for application code, but databases havent
>> >> caught up. So what steps can you take to put your SQL databases under
>> >> version control? Why should you start doing it? Read more to find out.
>> >>
>> >> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
>> >> _______________________________________________
>> >> Kaldi-developers mailing list
>> >> Kal...@li...
>> >> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>> >>
>> >
>> >
>> > ------------------------------------------------------------------------------
>> > Get your SQL database under version control now!
>> > Version control is standard for application code, but databases havent
>> > caught up. So what steps can you take to put your SQL databases under
>> > version control? Why should you start doing it? Read more to find out.
>> >
>> > http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
>> > _______________________________________________
>> > Kaldi-developers mailing list
>> > Kal...@li...
>> > https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>
>

Re: [Kaldi-developers] Problems in installing Kaldi

[Ji He <jv...@uw...>]

Thanks for your reply. We have BLAS, CBLAS and CLAPACK installed by root
admin. Let me check if these packages will be enough to build it, and how
to set the dependency. One easy solution would be compile Kaldi on my
laptop, but I prefer lab's machine so that other people can refer to it
later.

I looked at the Kaldi tutorial here:
http://kaldi.sourceforge.net/tutorial_setup.html
and instead of checking out version 1 code I checked out the trunk, i.e.
svn co https://kaldi.svn.sourceforge.net/svnroot/kaldi/trunk kaldi-trunk

Please let me know if there is a later version. Thanks.


On Wed, Jul 31, 2013 at 9:13 AM, Daniel Povey <dp...@gm...> wrote:

> Where did you get the instructions to download Kaldi?  I'm concerned
> that people are still getting out-of-date instructions with the "old"
> sourceforge location.
> Dan
>
>
> On Wed, Jul 31, 2013 at 8:26 AM, Arnab Ghoshal <ar...@gm...> wrote:
> > Kaldi needs some kind of linear algebra library. ATLAS is easily
> > obtained. Otherwise if your system has MKL, you could use that as
> > well. Check to see what messages install_atlas.sh generated (btw, you
> > are using an older version, since the install_atlas.sh has now moved
> > to tools/extras). The most common problem is that CPU throttling needs
> > to be disabled for installing ATLAS, but that requires root access. It
> > may be best to consult with your admin about ATLAS/MKL and to install
> > one if none is present.
> > -Arnab
> >
> > On Mon, Jul 29, 2013 at 1:35 AM, Ji He <jv...@uw...> wrote:
> >> Hi there,
> >>
> >> I heard that Kaldi is becoming popular these days and I want to try it
> >> myself. But I don't have access to root directory in my lab's machine,
> so I
> >> try to install it on my local space (and setting file dependencies
> etc.). I
> >> am not sure how to do this.
> >>
> >> Basically when I ran the normal installation steps, I got errors in
> >> ./configure (in src/), it says:
> >>
> >> On Linux: Checking for linear algebra header files ...
> >> Using ATLAS as the linear algebra library.
> >> Could not find libatlas.a in any of the obvious places... will try
> dynamic
> >> libraries.
> >> No libatlas.so in /usr/lib
> >> No libatlas.so in /usr/lib/atlas
> >> No libatlas.so in /usr/lib/atlas-sse2
> >> No libatlas.so in /usr/lib/atlas-sse3
> >> No libatlas.so in /usr/lib64
> >> No libatlas.so in /usr/lib64/atlas
> >> No libatlas.so in /usr/lib64/atlas-sse2
> >> No libatlas.so in /usr/lib64/atlas-sse3
> >> No libatlas.so in /usr/local/lib
> >> No libatlas.so in /usr/local/lib/atlas
> >> No libatlas.so in /usr/local/lib/atlas-sse2
> >> No libatlas.so in /usr/local/lib/atlas-sse3
> >> No libatlas.so in /usr/local/lib64
> >> No libatlas.so in /usr/local/lib64/atlas
> >> No libatlas.so in /usr/local/lib64/atlas-sse2
> >> No libatlas.so in /usr/local/lib64/atlas-sse3
> >> No libatlas.so in
> >> /s1/jvking/temp/Kaldi/kaldi-trunk/src/../tools/ATLAS/build/install/lib/
> >> No libatlas.so in /s1/jvking/temp/Kaldi/kaldi-trunk/tools/ATLAS/lib
> >> Could not find libatlas.so in any of the obvious places.
> >> ** Failed to configure ATLAS lbiraries ***
> >> **  ERROR   **
> >> **Configure cannot proceed automatically, but by editing kaldi.mk
> >> ** you may be able to proceed (replace [somewhere] with a directory),
> >> ** or install the ATLAS package on your machine,
> >> ** or try going to ../tools and running install_atlas.sh, and running
> >> ** this script (configure) again.
> >>
> >> I read how Kaldi is compiled and it seems I may need to edit the
> >>
> >> ATLASINC = [somewhere]/include
> >> ATLASLIBS = [somewhere]/liblapack.a [somewhere]/libcblas.a
> >> [somewhere]/libatlas.a [somewhere]/libf77blas.a
> >>
> >> lines in src/kaldi.mk, but I don't know where I should pointed it to.
> I also
> >> tried running ./tools/install_atlas.sh but have no idea what I should do
> >> after that step. I cannot find libatlas.a anywhere in my local
> directory,
> >> i.e. kaldi-trunk. I look forward to your quick reply.
> >>
> >> With regards,
> >> HE Ji
> >>
> >>
> ------------------------------------------------------------------------------
> >> Get your SQL database under version control now!
> >> Version control is standard for application code, but databases havent
> >> caught up. So what steps can you take to put your SQL databases under
> >> version control? Why should you start doing it? Read more to find out.
> >>
> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
> >> _______________________________________________
> >> Kaldi-developers mailing list
> >> Kal...@li...
> >> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
> >>
> >
> >
> ------------------------------------------------------------------------------
> > Get your SQL database under version control now!
> > Version control is standard for application code, but databases havent
> > caught up. So what steps can you take to put your SQL databases under
> > version control? Why should you start doing it? Read more to find out.
> >
> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
> > _______________________________________________
> > Kaldi-developers mailing list
> > Kal...@li...
> > https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>

Re: [Kaldi-developers] Problems in installing Kaldi

[Daniel P. <dp...@gm...>]

Where did you get the instructions to download Kaldi?  I'm concerned
that people are still getting out-of-date instructions with the "old"
sourceforge location.
Dan


On Wed, Jul 31, 2013 at 8:26 AM, Arnab Ghoshal <ar...@gm...> wrote:
> Kaldi needs some kind of linear algebra library. ATLAS is easily
> obtained. Otherwise if your system has MKL, you could use that as
> well. Check to see what messages install_atlas.sh generated (btw, you
> are using an older version, since the install_atlas.sh has now moved
> to tools/extras). The most common problem is that CPU throttling needs
> to be disabled for installing ATLAS, but that requires root access. It
> may be best to consult with your admin about ATLAS/MKL and to install
> one if none is present.
> -Arnab
>
> On Mon, Jul 29, 2013 at 1:35 AM, Ji He <jv...@uw...> wrote:
>> Hi there,
>>
>> I heard that Kaldi is becoming popular these days and I want to try it
>> myself. But I don't have access to root directory in my lab's machine, so I
>> try to install it on my local space (and setting file dependencies etc.). I
>> am not sure how to do this.
>>
>> Basically when I ran the normal installation steps, I got errors in
>> ./configure (in src/), it says:
>>
>> On Linux: Checking for linear algebra header files ...
>> Using ATLAS as the linear algebra library.
>> Could not find libatlas.a in any of the obvious places... will try dynamic
>> libraries.
>> No libatlas.so in /usr/lib
>> No libatlas.so in /usr/lib/atlas
>> No libatlas.so in /usr/lib/atlas-sse2
>> No libatlas.so in /usr/lib/atlas-sse3
>> No libatlas.so in /usr/lib64
>> No libatlas.so in /usr/lib64/atlas
>> No libatlas.so in /usr/lib64/atlas-sse2
>> No libatlas.so in /usr/lib64/atlas-sse3
>> No libatlas.so in /usr/local/lib
>> No libatlas.so in /usr/local/lib/atlas
>> No libatlas.so in /usr/local/lib/atlas-sse2
>> No libatlas.so in /usr/local/lib/atlas-sse3
>> No libatlas.so in /usr/local/lib64
>> No libatlas.so in /usr/local/lib64/atlas
>> No libatlas.so in /usr/local/lib64/atlas-sse2
>> No libatlas.so in /usr/local/lib64/atlas-sse3
>> No libatlas.so in
>> /s1/jvking/temp/Kaldi/kaldi-trunk/src/../tools/ATLAS/build/install/lib/
>> No libatlas.so in /s1/jvking/temp/Kaldi/kaldi-trunk/tools/ATLAS/lib
>> Could not find libatlas.so in any of the obvious places.
>> ** Failed to configure ATLAS lbiraries ***
>> **  ERROR   **
>> **Configure cannot proceed automatically, but by editing kaldi.mk
>> ** you may be able to proceed (replace [somewhere] with a directory),
>> ** or install the ATLAS package on your machine,
>> ** or try going to ../tools and running install_atlas.sh, and running
>> ** this script (configure) again.
>>
>> I read how Kaldi is compiled and it seems I may need to edit the
>>
>> ATLASINC = [somewhere]/include
>> ATLASLIBS = [somewhere]/liblapack.a [somewhere]/libcblas.a
>> [somewhere]/libatlas.a [somewhere]/libf77blas.a
>>
>> lines in src/kaldi.mk, but I don't know where I should pointed it to. I also
>> tried running ./tools/install_atlas.sh but have no idea what I should do
>> after that step. I cannot find libatlas.a anywhere in my local directory,
>> i.e. kaldi-trunk. I look forward to your quick reply.
>>
>> With regards,
>> HE Ji
>>
>> ------------------------------------------------------------------------------
>> Get your SQL database under version control now!
>> Version control is standard for application code, but databases havent
>> caught up. So what steps can you take to put your SQL databases under
>> version control? Why should you start doing it? Read more to find out.
>> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
>> _______________________________________________
>> Kaldi-developers mailing list
>> Kal...@li...
>> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>>
>
> ------------------------------------------------------------------------------
> Get your SQL database under version control now!
> Version control is standard for application code, but databases havent
> caught up. So what steps can you take to put your SQL databases under
> version control? Why should you start doing it? Read more to find out.
> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers

Re: [Kaldi-developers] Problems in installing Kaldi

[Arnab G. <ar...@gm...>]

Kaldi needs some kind of linear algebra library. ATLAS is easily
obtained. Otherwise if your system has MKL, you could use that as
well. Check to see what messages install_atlas.sh generated (btw, you
are using an older version, since the install_atlas.sh has now moved
to tools/extras). The most common problem is that CPU throttling needs
to be disabled for installing ATLAS, but that requires root access. It
may be best to consult with your admin about ATLAS/MKL and to install
one if none is present.
-Arnab

On Mon, Jul 29, 2013 at 1:35 AM, Ji He <jv...@uw...> wrote:
> Hi there,
>
> I heard that Kaldi is becoming popular these days and I want to try it
> myself. But I don't have access to root directory in my lab's machine, so I
> try to install it on my local space (and setting file dependencies etc.). I
> am not sure how to do this.
>
> Basically when I ran the normal installation steps, I got errors in
> ./configure (in src/), it says:
>
> On Linux: Checking for linear algebra header files ...
> Using ATLAS as the linear algebra library.
> Could not find libatlas.a in any of the obvious places... will try dynamic
> libraries.
> No libatlas.so in /usr/lib
> No libatlas.so in /usr/lib/atlas
> No libatlas.so in /usr/lib/atlas-sse2
> No libatlas.so in /usr/lib/atlas-sse3
> No libatlas.so in /usr/lib64
> No libatlas.so in /usr/lib64/atlas
> No libatlas.so in /usr/lib64/atlas-sse2
> No libatlas.so in /usr/lib64/atlas-sse3
> No libatlas.so in /usr/local/lib
> No libatlas.so in /usr/local/lib/atlas
> No libatlas.so in /usr/local/lib/atlas-sse2
> No libatlas.so in /usr/local/lib/atlas-sse3
> No libatlas.so in /usr/local/lib64
> No libatlas.so in /usr/local/lib64/atlas
> No libatlas.so in /usr/local/lib64/atlas-sse2
> No libatlas.so in /usr/local/lib64/atlas-sse3
> No libatlas.so in
> /s1/jvking/temp/Kaldi/kaldi-trunk/src/../tools/ATLAS/build/install/lib/
> No libatlas.so in /s1/jvking/temp/Kaldi/kaldi-trunk/tools/ATLAS/lib
> Could not find libatlas.so in any of the obvious places.
> ** Failed to configure ATLAS lbiraries ***
> **  ERROR   **
> **Configure cannot proceed automatically, but by editing kaldi.mk
> ** you may be able to proceed (replace [somewhere] with a directory),
> ** or install the ATLAS package on your machine,
> ** or try going to ../tools and running install_atlas.sh, and running
> ** this script (configure) again.
>
> I read how Kaldi is compiled and it seems I may need to edit the
>
> ATLASINC = [somewhere]/include
> ATLASLIBS = [somewhere]/liblapack.a [somewhere]/libcblas.a
> [somewhere]/libatlas.a [somewhere]/libf77blas.a
>
> lines in src/kaldi.mk, but I don't know where I should pointed it to. I also
> tried running ./tools/install_atlas.sh but have no idea what I should do
> after that step. I cannot find libatlas.a anywhere in my local directory,
> i.e. kaldi-trunk. I look forward to your quick reply.
>
> With regards,
> HE Ji
>
> ------------------------------------------------------------------------------
> Get your SQL database under version control now!
> Version control is standard for application code, but databases havent
> caught up. So what steps can you take to put your SQL databases under
> version control? Why should you start doing it? Read more to find out.
> http://pubads.g.doubleclick.net/gampad/clk?id=49501711&iu=/4140/ostg.clktrk
> _______________________________________________
> Kaldi-developers mailing list
> Kal...@li...
> https://lists.sourceforge.net/lists/listinfo/kaldi-developers
>

[Kaldi-developers] Problems in installing Kaldi

[Ji He <jv...@uw...>]

Hi there,

I heard that Kaldi is becoming popular these days and I want to try it
myself. But I don't have access to root directory in my lab's machine, so I
try to install it on my local space (and setting file dependencies etc.). I
am not sure how to do this.

Basically when I ran the normal installation steps, I got errors in
./configure (in src/), it says:

On Linux: Checking for linear algebra header files ...
Using ATLAS as the linear algebra library.
Could not find libatlas.a in any of the obvious places... will try dynamic
libraries.
No libatlas.so in /usr/lib
No libatlas.so in /usr/lib/atlas
No libatlas.so in /usr/lib/atlas-sse2
No libatlas.so in /usr/lib/atlas-sse3
No libatlas.so in /usr/lib64
No libatlas.so in /usr/lib64/atlas
No libatlas.so in /usr/lib64/atlas-sse2
No libatlas.so in /usr/lib64/atlas-sse3
No libatlas.so in /usr/local/lib
No libatlas.so in /usr/local/lib/atlas
No libatlas.so in /usr/local/lib/atlas-sse2
No libatlas.so in /usr/local/lib/atlas-sse3
No libatlas.so in /usr/local/lib64
No libatlas.so in /usr/local/lib64/atlas
No libatlas.so in /usr/local/lib64/atlas-sse2
No libatlas.so in /usr/local/lib64/atlas-sse3
No libatlas.so in
/s1/jvking/temp/Kaldi/kaldi-trunk/src/../tools/ATLAS/build/install/lib/
No libatlas.so in /s1/jvking/temp/Kaldi/kaldi-trunk/tools/ATLAS/lib
Could not find libatlas.so in any of the obvious places.
** Failed to configure ATLAS lbiraries ***
**  ERROR   **
**Configure cannot proceed automatically, but by editing kaldi.mk
** you may be able to proceed (replace [somewhere] with a directory),
** or install the ATLAS package on your machine,
** or try going to ../tools and running install_atlas.sh, and running
** this script (configure) again.

I read how Kaldi is compiled and it seems I may need to edit the

ATLASINC = [somewhere]/include
ATLASLIBS = [somewhere]/liblapack.a [somewhere]/libcblas.a
[somewhere]/libatlas.a [somewhere]/libf77blas.a

lines in src/kaldi.mk, but I don't know where I should pointed it to. I
also tried running ./tools/install_atlas.sh but have no idea what I should
do after that step. I cannot find libatlas.a anywhere in my local
directory, i.e. kaldi-trunk. I look forward to your quick reply.

With regards,
HE Ji

[Kaldi-developers] [Jenkins] Kaldi automatic build and test

[<jen...@a2...>]

Kaldi - Build # 19 - Successful:

Check console output at http://jenkins.a2ialab.com/jenkins/job/Kaldi/19/ to view the results.

[Kaldi-developers] [Jenkins] Kaldi automatic build and test

[<jen...@a2...>]

Kaldi - Build # 18 - Successful:

Check console output at http://jenkins.a2ialab.com/jenkins/job/Kaldi/18/ to view the results.