Sfdwhf

My cat mixes up the floors in my building. How can I help him?

Intern applicant asking for compensation equivalent to that of permanent employee

If I deleted a game I lost the disc for, can I reinstall it digitally?

Why exactly do action photographers need high fps burst cameras?

Normalization for two bulk RNA-Seq samples to enable reliable fold-change estimation between genes

Can making a creature unable to attack after it has been assigned as an attacker remove it from combat?

Can an insurance company drop you after receiving a bill and refusing to pay?

Digits in an algebraic irrational number

Why do members of Congress in committee hearings ask witnesses the same question multiple times?

Why publish a research paper when a blog post or a lecture slide can have more citation count than a journal paper?

How would an AI self awareness kill switch work?

CREATE ASSEMBLY System.DirectoryServices.AccountManagement.dll without enabling TRUSTWORTHY

Why do neural networks need so many training examples to perform?

Incorporating research and background: How much is too much?

Why do no American passenger airlines still operate dedicated cargo flights?

How to prevent cleaner from hanging my lock screen in Ubuntu 16.04

Is it a fallacy if someone claims they need an explanation for every word of your argument to the point where they don't understand common terms?

What is the purpose of easy combat scenarios that don't need resource expenditure?

How to deal with an incendiary email that was recalled

How to say "Brexit" in Latin?

Why would space fleets be aligned?

Injecting creativity into a cookbook

How can I get my players to come to the game session after agreeing to a date?

Why did the villain in the first Men in Black movie care about Earth's Cockroaches?

Speech-recognition app to convert MP3 to text?

Is there any voice recognition software(G.U.I) for ubuntu destop?Recommendation for a dictation softwareSpeech to text software for notesConvert speech (mp3 audio files) to textWhat program can I use to convert text into binary numbers?How can I install and use text-to-speech software?Software for speech transcriptionWhy does the Julius speech recognition engine return a segmentation fault when passing a WAV file?simple Speech recognition under linuxSpeech recognition for regional languageSimple Speech RecognitionWhat is a good speech recognition software?Convert speech (mp3 audio files) to textSpeech recognition for programming

24

13

Does any one know of an application that can convert audio to text? I'm running ubuntu 12.04 LTS.

software-recommendation speech-recognition

share|improve this question

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

asked Jul 9 '12 at 11:33

KopanoKopano

121113

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  I assume it is spoken text. Which language is that text in?
  
  – Martin Ueding
  Jul 9 '12 at 11:33
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  The speech text is in simple english.
  
  – Kopano
  Jul 9 '12 at 14:33
  

  
  
  
  

add a comment | 

24

13

Does any one know of an application that can convert audio to text? I'm running ubuntu 12.04 LTS.

software-recommendation speech-recognition

share|improve this question

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

asked Jul 9 '12 at 11:33

KopanoKopano

121113

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  I assume it is spoken text. Which language is that text in?
  
  – Martin Ueding
  Jul 9 '12 at 11:33
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  The speech text is in simple english.
  
  – Kopano
  Jul 9 '12 at 14:33
  

  
  
  
  

add a comment | 

Does any one know of an application that can convert audio to text? I'm running ubuntu 12.04 LTS.

software-recommendation speech-recognition

share|improve this question

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

asked Jul 9 '12 at 11:33

KopanoKopano

121113

share|improve this question

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

asked Jul 9 '12 at 11:33

KopanoKopano

121113

share|improve this question

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

asked Jul 9 '12 at 11:33

KopanoKopano

121113

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

edited Jul 9 '12 at 15:07

Eliah Kagan

82.4k22227368

asked Jul 9 '12 at 11:33

KopanoKopano

121113

asked Jul 9 '12 at 11:33

KopanoKopano

121113

4 Answers
4

active

oldest

votes

19

The software you can use is CMUSphinx. Unlike suggested in another answer Julius is not suitable because it requires models. Models for large vocabulary speech recognition are not available for Julius.

You can use pocketsphinx to convert audio file. Those two commands must do the work. First you convert the file to the required format and then you recognize it:

ffmpeg -i file.mp3 -ar 16000 -ac 1 file.wav

The run pocketsphinx

pocketsphinx_continuous -infile file.wav 2> pocketsphinx.log > result.txt

Result will be stored in result.txt.

share|improve this answer

edited 24 mins ago

Pablo Bianchi

2,77821533

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  also, as an addition to this answer, there's a cool demo of both speech recognition and voice command tools here: youtube.com/…
  
  – Daithí
  Jan 8 '15 at 10:22
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  How do you add an acoustic model to the system?
  
  – jarno
  Feb 8 '15 at 13:38
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  You just download it and unpack, there is no such thing as "add to the system"
  
  – Nikolay Shmyrev
  Feb 8 '15 at 13:56
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @NikolayShmyrev Where should I unpack it so that pocketsphinx_continuous finds it?
  
  – jarno
  Feb 8 '15 at 14:14
  

  
  
  
  


• 
  
  
  

  
  4
  

  
  
  
  
  
  

  
  
  Well, I installed packages pocketsphinx-utils, pocketsphinx-hmm-en-hub4wsj and pocketsphinx-lm-en-hub4 in universe repository of Ubuntu 14.04. Then pocketsphinx_continuous -infile file.wav -hmm en_US/hub4wsj_sc_8k -lm en_US/hub4.5000.DMP 2> pocketsphinx.log worked. Maybe they are not optimal packages, but they were best matches I could find in the repositories.
  
  – jarno
  Feb 8 '15 at 15:05
  

  
  
  
  

 | 
show 4 more comments

10

I you are looking to convert speech to text you could try opening up your Ubuntu Software Center and search for Julius

Description

"Julius" is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers.

Or another option that isn't in the Software Center is Simon

... is an open-source speech recognition program and replaces the mouse and keyboard.

Reference Links

http://julius.sourceforge.jp/en_index.php

http://sourceforge.net/projects/speech2text/

http://simon-listens.org/index.php?id=122&L=1

share|improve this answer

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

add a comment | 

9

I know this is old, but to expand on Nikolay's answer and hopefully save someone some time in the future, in order to get an up-to-date version of pocketsphinx working you need to compile it from the github or sourceforge repository (not sure which is kept more up to date). Note the -j8 means run 8 separate jobs in parallel if possible; if you have more CPU cores you can increase the number.

git clone https://github.com/cmusphinx/sphinxbase.git

cd sphinxbase

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

git clone https://github.com/cmusphinx/pocketsphinx.git

cd pocketsphinx

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

Then, from: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/US%20English/
download the newest versions of cmusphinx-en-us-....tar.gz and en-70k-....lm.gz

tar -xzf cmusphinx-en-us-....tar.gz

gunzip en-70k-....lm.gz

Then you can finally proceed with the steps from Nikolay's answer:

ffmpeg -i book.mp3 -ar 16000 -ac 1 book.wav

pocketsphinx_continuous -infile book.wav 

    -hmm cmusphinx-en-us-8khz-5.2 -lm en-70k-0.2.lm 

    2>pocketsphinx.log >book.txt

Sphinx works alright. I wouldn't rely on it to make a readable version of the text, but it's good enough that you can search it if you're looking for a particular quote. That works especially well if you use a search algorithm like Xapian (http://www.lesbonscomptes.com/recoll/) which accepts wildcards and doesn't require exact search expressions.

Hope this helps.

share|improve this answer

edited Jan 17 '18 at 10:43

nickcrabtree

571414

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

• 
  
  
  

  
  3
  

  
  
  
  
  
  

  
  
  every thing works like a charm but in my case i had to run following command to fix pocketsphinx_continuous: error while loading shared libraries: libpocketsphinx.so.3: cannot open shared object file: No such file or directory -------> export LD_LIBRARY_PATH=/usr/local/lib -------> export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig
  
  – Vijay Dohare
  Sep 19 '17 at 11:30
  
  
  

  
  
  
  

add a comment | 

1

You can use speechpad.pw transcription panel

See video of using transcription

share|improve this answer

answered Jul 10 '16 at 20:37

alexeialexei

211

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  That looks cool although I don't think it answers the question which was to get a transcription of an existing file. That being said, I just tried Sphinx and it failed miserably... the transcription was 99.9% wrong.
  
  – Alexis Wilke
  Nov 10 '17 at 18:47
  

  
  
  
  

add a comment | 

Your Answer

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "89"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2faskubuntu.com%2fquestions%2f161515%2fspeech-recognition-app-to-convert-mp3-to-text%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

19

The software you can use is CMUSphinx. Unlike suggested in another answer Julius is not suitable because it requires models. Models for large vocabulary speech recognition are not available for Julius.

You can use pocketsphinx to convert audio file. Those two commands must do the work. First you convert the file to the required format and then you recognize it:

ffmpeg -i file.mp3 -ar 16000 -ac 1 file.wav

The run pocketsphinx

pocketsphinx_continuous -infile file.wav 2> pocketsphinx.log > result.txt

Result will be stored in result.txt.

share|improve this answer

edited 24 mins ago

Pablo Bianchi

2,77821533

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  also, as an addition to this answer, there's a cool demo of both speech recognition and voice command tools here: youtube.com/…
  
  – Daithí
  Jan 8 '15 at 10:22
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  How do you add an acoustic model to the system?
  
  – jarno
  Feb 8 '15 at 13:38
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  You just download it and unpack, there is no such thing as "add to the system"
  
  – Nikolay Shmyrev
  Feb 8 '15 at 13:56
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @NikolayShmyrev Where should I unpack it so that pocketsphinx_continuous finds it?
  
  – jarno
  Feb 8 '15 at 14:14
  

  
  
  
  


• 
  
  
  

  
  4
  

  
  
  
  
  
  

  
  
  Well, I installed packages pocketsphinx-utils, pocketsphinx-hmm-en-hub4wsj and pocketsphinx-lm-en-hub4 in universe repository of Ubuntu 14.04. Then pocketsphinx_continuous -infile file.wav -hmm en_US/hub4wsj_sc_8k -lm en_US/hub4.5000.DMP 2> pocketsphinx.log worked. Maybe they are not optimal packages, but they were best matches I could find in the repositories.
  
  – jarno
  Feb 8 '15 at 15:05
  

  
  
  
  

 | 
show 4 more comments

19

The software you can use is CMUSphinx. Unlike suggested in another answer Julius is not suitable because it requires models. Models for large vocabulary speech recognition are not available for Julius.

You can use pocketsphinx to convert audio file. Those two commands must do the work. First you convert the file to the required format and then you recognize it:

ffmpeg -i file.mp3 -ar 16000 -ac 1 file.wav

The run pocketsphinx

pocketsphinx_continuous -infile file.wav 2> pocketsphinx.log > result.txt

Result will be stored in result.txt.

share|improve this answer

edited 24 mins ago

Pablo Bianchi

2,77821533

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  also, as an addition to this answer, there's a cool demo of both speech recognition and voice command tools here: youtube.com/…
  
  – Daithí
  Jan 8 '15 at 10:22
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  How do you add an acoustic model to the system?
  
  – jarno
  Feb 8 '15 at 13:38
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  You just download it and unpack, there is no such thing as "add to the system"
  
  – Nikolay Shmyrev
  Feb 8 '15 at 13:56
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @NikolayShmyrev Where should I unpack it so that pocketsphinx_continuous finds it?
  
  – jarno
  Feb 8 '15 at 14:14
  

  
  
  
  


• 
  
  
  

  
  4
  

  
  
  
  
  
  

  
  
  Well, I installed packages pocketsphinx-utils, pocketsphinx-hmm-en-hub4wsj and pocketsphinx-lm-en-hub4 in universe repository of Ubuntu 14.04. Then pocketsphinx_continuous -infile file.wav -hmm en_US/hub4wsj_sc_8k -lm en_US/hub4.5000.DMP 2> pocketsphinx.log worked. Maybe they are not optimal packages, but they were best matches I could find in the repositories.
  
  – jarno
  Feb 8 '15 at 15:05
  

  
  
  
  

 | 
show 4 more comments

The software you can use is CMUSphinx. Unlike suggested in another answer Julius is not suitable because it requires models. Models for large vocabulary speech recognition are not available for Julius.

You can use pocketsphinx to convert audio file. Those two commands must do the work. First you convert the file to the required format and then you recognize it:

ffmpeg -i file.mp3 -ar 16000 -ac 1 file.wav

The run pocketsphinx

pocketsphinx_continuous -infile file.wav 2> pocketsphinx.log > result.txt

Result will be stored in result.txt.

share|improve this answer

edited 24 mins ago

Pablo Bianchi

2,77821533

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

ffmpeg -i file.mp3 -ar 16000 -ac 1 file.wav

pocketsphinx_continuous -infile file.wav 2> pocketsphinx.log > result.txt

share|improve this answer

edited 24 mins ago

Pablo Bianchi

2,77821533

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

edited 24 mins ago

Pablo Bianchi

2,77821533

edited 24 mins ago

Pablo Bianchi

2,77821533

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

answered Feb 20 '14 at 20:24

Nikolay ShmyrevNikolay Shmyrev

37729

10

I you are looking to convert speech to text you could try opening up your Ubuntu Software Center and search for Julius

Description

"Julius" is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers.

Or another option that isn't in the Software Center is Simon

... is an open-source speech recognition program and replaces the mouse and keyboard.

Reference Links

http://julius.sourceforge.jp/en_index.php

http://sourceforge.net/projects/speech2text/

http://simon-listens.org/index.php?id=122&L=1

share|improve this answer

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

add a comment | 

10

I you are looking to convert speech to text you could try opening up your Ubuntu Software Center and search for Julius

Description

"Julius" is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers.

Or another option that isn't in the Software Center is Simon

... is an open-source speech recognition program and replaces the mouse and keyboard.

Reference Links

http://julius.sourceforge.jp/en_index.php

http://sourceforge.net/projects/speech2text/

http://simon-listens.org/index.php?id=122&L=1

share|improve this answer

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

add a comment | 

I you are looking to convert speech to text you could try opening up your Ubuntu Software Center and search for Julius

Description

"Julius" is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers.

Or another option that isn't in the Software Center is Simon

... is an open-source speech recognition program and replaces the mouse and keyboard.

Reference Links

http://julius.sourceforge.jp/en_index.php

http://sourceforge.net/projects/speech2text/

http://simon-listens.org/index.php?id=122&L=1

share|improve this answer

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

share|improve this answer

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

answered Jul 9 '12 at 11:54

CoalaWebCoalaWeb

2,7441628

9

I know this is old, but to expand on Nikolay's answer and hopefully save someone some time in the future, in order to get an up-to-date version of pocketsphinx working you need to compile it from the github or sourceforge repository (not sure which is kept more up to date). Note the -j8 means run 8 separate jobs in parallel if possible; if you have more CPU cores you can increase the number.

git clone https://github.com/cmusphinx/sphinxbase.git

cd sphinxbase

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

git clone https://github.com/cmusphinx/pocketsphinx.git

cd pocketsphinx

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

Then, from: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/US%20English/
download the newest versions of cmusphinx-en-us-....tar.gz and en-70k-....lm.gz

tar -xzf cmusphinx-en-us-....tar.gz

gunzip en-70k-....lm.gz

Then you can finally proceed with the steps from Nikolay's answer:

ffmpeg -i book.mp3 -ar 16000 -ac 1 book.wav

pocketsphinx_continuous -infile book.wav 

    -hmm cmusphinx-en-us-8khz-5.2 -lm en-70k-0.2.lm 

    2>pocketsphinx.log >book.txt

Sphinx works alright. I wouldn't rely on it to make a readable version of the text, but it's good enough that you can search it if you're looking for a particular quote. That works especially well if you use a search algorithm like Xapian (http://www.lesbonscomptes.com/recoll/) which accepts wildcards and doesn't require exact search expressions.

Hope this helps.

share|improve this answer

edited Jan 17 '18 at 10:43

nickcrabtree

571414

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

• 
  
  
  

  
  3
  

  
  
  
  
  
  

  
  
  every thing works like a charm but in my case i had to run following command to fix pocketsphinx_continuous: error while loading shared libraries: libpocketsphinx.so.3: cannot open shared object file: No such file or directory -------> export LD_LIBRARY_PATH=/usr/local/lib -------> export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig
  
  – Vijay Dohare
  Sep 19 '17 at 11:30
  
  
  

  
  
  
  

add a comment | 

9

I know this is old, but to expand on Nikolay's answer and hopefully save someone some time in the future, in order to get an up-to-date version of pocketsphinx working you need to compile it from the github or sourceforge repository (not sure which is kept more up to date). Note the -j8 means run 8 separate jobs in parallel if possible; if you have more CPU cores you can increase the number.

git clone https://github.com/cmusphinx/sphinxbase.git

cd sphinxbase

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

git clone https://github.com/cmusphinx/pocketsphinx.git

cd pocketsphinx

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

Then, from: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/US%20English/
download the newest versions of cmusphinx-en-us-....tar.gz and en-70k-....lm.gz

tar -xzf cmusphinx-en-us-....tar.gz

gunzip en-70k-....lm.gz

Then you can finally proceed with the steps from Nikolay's answer:

ffmpeg -i book.mp3 -ar 16000 -ac 1 book.wav

pocketsphinx_continuous -infile book.wav 

    -hmm cmusphinx-en-us-8khz-5.2 -lm en-70k-0.2.lm 

    2>pocketsphinx.log >book.txt

Sphinx works alright. I wouldn't rely on it to make a readable version of the text, but it's good enough that you can search it if you're looking for a particular quote. That works especially well if you use a search algorithm like Xapian (http://www.lesbonscomptes.com/recoll/) which accepts wildcards and doesn't require exact search expressions.

Hope this helps.

share|improve this answer

edited Jan 17 '18 at 10:43

nickcrabtree

571414

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

• 
  
  
  

  
  3
  

  
  
  
  
  
  

  
  
  every thing works like a charm but in my case i had to run following command to fix pocketsphinx_continuous: error while loading shared libraries: libpocketsphinx.so.3: cannot open shared object file: No such file or directory -------> export LD_LIBRARY_PATH=/usr/local/lib -------> export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig
  
  – Vijay Dohare
  Sep 19 '17 at 11:30
  
  
  

  
  
  
  

add a comment | 

I know this is old, but to expand on Nikolay's answer and hopefully save someone some time in the future, in order to get an up-to-date version of pocketsphinx working you need to compile it from the github or sourceforge repository (not sure which is kept more up to date). Note the -j8 means run 8 separate jobs in parallel if possible; if you have more CPU cores you can increase the number.

git clone https://github.com/cmusphinx/sphinxbase.git

cd sphinxbase

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

git clone https://github.com/cmusphinx/pocketsphinx.git

cd pocketsphinx

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

Then, from: https://sourceforge.net/projects/cmusphinx/files/Acoustic%20and%20Language%20Models/US%20English/
download the newest versions of cmusphinx-en-us-....tar.gz and en-70k-....lm.gz

tar -xzf cmusphinx-en-us-....tar.gz

gunzip en-70k-....lm.gz

Then you can finally proceed with the steps from Nikolay's answer:

ffmpeg -i book.mp3 -ar 16000 -ac 1 book.wav

pocketsphinx_continuous -infile book.wav 

    -hmm cmusphinx-en-us-8khz-5.2 -lm en-70k-0.2.lm 

    2>pocketsphinx.log >book.txt

Sphinx works alright. I wouldn't rely on it to make a readable version of the text, but it's good enough that you can search it if you're looking for a particular quote. That works especially well if you use a search algorithm like Xapian (http://www.lesbonscomptes.com/recoll/) which accepts wildcards and doesn't require exact search expressions.

Hope this helps.

share|improve this answer

edited Jan 17 '18 at 10:43

nickcrabtree

571414

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

git clone https://github.com/cmusphinx/sphinxbase.git

cd sphinxbase

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

git clone https://github.com/cmusphinx/pocketsphinx.git

cd pocketsphinx

./autogen.sh

./configure

make -j8

make -j8 check

sudo make install

cd ..

tar -xzf cmusphinx-en-us-....tar.gz

gunzip en-70k-....lm.gz

ffmpeg -i book.mp3 -ar 16000 -ac 1 book.wav

pocketsphinx_continuous -infile book.wav 

    -hmm cmusphinx-en-us-8khz-5.2 -lm en-70k-0.2.lm 

    2>pocketsphinx.log >book.txt

share|improve this answer

edited Jan 17 '18 at 10:43

nickcrabtree

571414

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

edited Jan 17 '18 at 10:43

nickcrabtree

571414

edited Jan 17 '18 at 10:43

nickcrabtree

571414

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

answered Apr 25 '17 at 5:01

Jonathan Perry-HoutsJonathan Perry-Houts

9111

1

You can use speechpad.pw transcription panel

See video of using transcription

share|improve this answer

answered Jul 10 '16 at 20:37

alexeialexei

211

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  That looks cool although I don't think it answers the question which was to get a transcription of an existing file. That being said, I just tried Sphinx and it failed miserably... the transcription was 99.9% wrong.
  
  – Alexis Wilke
  Nov 10 '17 at 18:47
  

  
  
  
  

add a comment | 

1

You can use speechpad.pw transcription panel

See video of using transcription

share|improve this answer

answered Jul 10 '16 at 20:37

alexeialexei

211

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  That looks cool although I don't think it answers the question which was to get a transcription of an existing file. That being said, I just tried Sphinx and it failed miserably... the transcription was 99.9% wrong.
  
  – Alexis Wilke
  Nov 10 '17 at 18:47
  

  
  
  
  

add a comment | 

You can use speechpad.pw transcription panel

See video of using transcription

share|improve this answer

answered Jul 10 '16 at 20:37

alexeialexei

211

share|improve this answer

answered Jul 10 '16 at 20:37

alexeialexei

211

answered Jul 10 '16 at 20:37

alexeialexei

211

answered Jul 10 '16 at 20:37

alexeialexei

211