mattlivingston / voiceid Goto Github PK

What steps will reproduce the problem?
1.Use db.match_voice() without gender argument

What is the expected output? What do you see instead?
It should give the output, instead raise error that 4 arguments required. Even 
with the use of gender it gives error

  File "/usr/local/lib/python2.7/dist-packages/voiceid/db.py", line 370, in match_voice
    gender, self.get_path())
  File "/usr/local/lib/python2.7/dist-packages/voiceid/fm.py", line 741, in wav_vs_gmm
    + gender + '.' + gmm_name + '.seg')
  File "/usr/local/lib/python2.7/dist-packages/voiceid/utils.py", line 102, in ensure_file_exists
    % filename)
IOError: File ash_.ident.M.ashu.gmm.seg doesn't exist or not correctly created

Four wav files with following specifications :
       codec : PCM s16 LE(araw)
       channels : Mono
       Sample rate : 8000 Hz
       Bits per sample : 16

with the help of sox removing silence & with one wav file built model  
        vid = "vid" + " -s " +  MR549a7b54b7143a42d04eaa69 + " -g " + wavfile
        proc = subprocess.call([vid], shell=True)
------------- MR549a7b54b7143a42d04eaa69.gmm.

Trying to Find voice match with remaining wav files by following :
-----------vid = "vid -i " +  wavfile  + " -f json -n -u"
           subprocess.call([vid], shell=True)

out of remaining three wav files , two had duration above 1min 30 seconds and 
other had only 25 sec of duration.

problems?
1. For the duration of 25 sec wav file , it gives me The system identified this 
speaker as wrong id. Ex : 'MR54585b7de75e4a1c58fc0785'!

What is the expected output? What do you see instead?
Should match same voice identification.

What version of the product are you using? On what operating system?
Centos 6.6

Please provide any additional information below.

Hi,

I'm just  downloaded your speaker identification system and I was trying to 
train the system. I ran into some problem when I passed a wav file that I 
created for training purses:

Traceback (most recent call last):
  File "./voiceid.py", line 1391, in <module>
    build_gmm(file_basename,speaker)
  File "./voiceid.py", line 1009, in build_gmm
    diarization(file_basename)
  File "./voiceid.py", line 1193, in diarization
    ensure_file_exists(filebasename+'.seg')
  File "./voiceid.py", line 741, in ensure_file_exists
    raise Exception("File %s doesn't exist or not correctly created"  % filename)
Exception: File octav_v1.seg doesn't exist or not correctly created

How can I go about creating the .seg file?

Thanks!

After tagging audio samples with vid in interactive mode, it then tries to 
update its database for several minutes, during which time I see several errors 
like:

    Traceback (most recent call last):
      File "/usr/lib/python2.7/threading.py", line 551, in __bootstrap_inner
        self.run()
      File "/usr/lib/python2.7/threading.py", line 504, in run
        self.__target(*self.__args, **self.__kwargs)
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/sr.py", line 1131, in _build_model_wrapper
        self[cluster].gender,self[cluster].value)
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/db.py", line 235, in add_model
        gender, self.get_path())
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/fm.py", line 739, in wav_vs_gmm
        + '  --sSetLabel=add --sByCluster ' + filebasename)
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/utils.py", line 79, in start_subprocess
        raise err
    OSError: Subprocess <subprocess.Popen object at 0x2354c90> closed unexpectedly [java -Xmx256M -cp /usr/local/project/.env/local/share/voiceid/LIUM_SpkDiarization-4.7.jar fr.lium.spkDiarization.programs.MScore --sInputMask=%s.seg --fInputMask=%s.wav --sOutputMask=%s.ident.M.az0001.gmm.seg --sOutputFormat=seg,UTF8 --fInputDesc=audio2sphinx,1:3:2:0:0:0,13,1:0:300:4 --tInputMask=/home/chris/.voiceid/gmm_db/M/az_tmp_gmms/az0001.gmm --sTop=8,/usr/local/project/.env/local/share/voiceid/ubm.gmm  --sSetLabel=add --sByCluster /tmp/testfile035/az3]

Should I be concerned by this? Does this mean the training samples are being 
corrupted or lost?

I had a lot of trouble getting gstreamer to work on Mac OS X which pinnacled in 
the fact that it refused to get a wav of an h264 AAC video. What I did in the 
end was to replace the subprocess call in file_2_wav (fm.py:79) using the 
following command:

utils.start_subprocess("ffmpeg -i '" + filename
           + "-vn -acodec pcm_s16le -ar 16000 -ac 1 -f wav " + name + ".wav ")

which spits out a wav coded correctly as demanded in the doc.

Hence I recommend using ffmpeg instead of gstreamer in future versions. Ffmpeg 
is widely available for the systems voiceid supports. Unless there are some 
issues with the license, of course. 

Use attached patches. Summary:

#1
    Port voiceidplayer to pubsub api v3

#2
    Port onevoiceidplayer to pubsub api v3

What steps will reproduce the problem?

1. vid -j /Library/Frameworks/Python.framework/Versions/2.7/share/voiceid/ -b 
/Library/Frameworks/Python.framework/Versions/2.7/share/voiceid/ -s GERARD -g 
/Volumes/Media/Voices/Gerard.wav 
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/vid", line 166, in <module>
    default_db.add_model(file_basename, speaker)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/voiceid/db.py", line 181, in add_model
    fm.build_gmm(basefilename, identifier)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/voiceid/fm.py", line 315, in build_gmm
    diarization_standard(filebasename)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/voiceid/fm.py", line 524, in diarization_standard
    + filebasename)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/voiceid/utils.py", line 79, in start_subprocess
    raise err
OSError: Subprocess <subprocess.Popen object at 0x6eb1d0> closed unexpectedly 
[java -Xmx2048m -jar 
/Library/Frameworks/Python.framework/Versions/2.7/share/voiceid/ 
fr.lium.spkDiarization.system.Diarization --fInputMask=%s.wav 
--sOutputMask=%s.seg --doCEClustering /Volumes/Media/Voices/Gerard_]

It's best practice to install Python projects into virtual environments. So, 
adapting your installation instructions, I did:

    sudo apt-get install -y python2.7 python-wxgtk2.8 openjdk-7-jdk gstreamer0.10-plugins-base gstreamer0.10-plugins-good gstreamer0.10-plugins-bad gstreamer0.10-plugins-ugly gstreamer-tools sox mplayer python-setuptools
    virtualenv --system-site-packages .env
    . .env/bin/activate
    pip install MplayerCtrl
    svn checkout http://voiceid.googlecode.com/svn/trunk voiceid
    cd voiceid
    python setup.py install

This installs fine, but when I attempt to run the `vid` command, I received the 
error:

    IOError: File /usr/local/myproject/.env/local/share/voiceid/LIUM_SpkDiarization-4.7.jar doesn't exist or not correctly created

This is because CONFIGURATION.LIUM_JAR is hardcoded to look in /local/share, 
but virtualenv creates a `local/` and a `share/`, but no `local/share`. I fixed 
this by symlinking `share/` into `local/`, but it might be easier to modify 
your code to check both locations.

I have installed all dependencies and test on ubuntu12.04.


When I tried vid -i INPUT_FILE -u, I've got the following messages:

converting_file
diarization
*** buffer overflow detected ***: sphinx_fe terminated
======= Backtrace: =========
/lib/i386-linux-gnu/libc.so.6(__fortify_fail+0x45)[0xb75dedd5]
/lib/i386-linux-gnu/libc.so.6(+0xfebaa)[0xb75ddbaa]
/lib/i386-linux-gnu/libc.so.6(+0xfdedd)[0xb75dcedd]
sphinx_fe[0x8049aef]
sphinx_fe[0x804ae3c]
sphinx_fe[0x8048fc6]
/lib/i386-linux-gnu/libc.so.6(__libc_start_main+0xf3)[0xb74f84d3]
sphinx_fe[0x8049025]
======= Memory map: ========
08048000-0804e000 r-xp 00000000 08:01 1067556    /usr/bin/sphinx_fe
0804e000-0804f000 r--p 00005000 08:01 1067556    /usr/bin/sphinx_fe
0804f000-08050000 rw-p 00006000 08:01 1067556    /usr/bin/sphinx_fe
09299000-092ba000 rw-p 00000000 00:00 0          [heap]
b7482000-b749e000 r-xp 00000000 08:01 394166     
/lib/i386-linux-gnu/libgcc_s.so.1
b749e000-b749f000 r--p 0001b000 08:01 394166     
/lib/i386-linux-gnu/libgcc_s.so.1
b749f000-b74a0000 rw-p 0001c000 08:01 394166     
/lib/i386-linux-gnu/libgcc_s.so.1
b74b2000-b74b3000 rw-p 00000000 00:00 0 
b74b3000-b74dd000 r-xp 00000000 08:01 394177     
/lib/i386-linux-gnu/libm-2.15.so
b74dd000-b74de000 r--p 00029000 08:01 394177     
/lib/i386-linux-gnu/libm-2.15.so
b74de000-b74df000 rw-p 0002a000 08:01 394177     
/lib/i386-linux-gnu/libm-2.15.so
b74df000-b767e000 r-xp 00000000 08:01 394145     
/lib/i386-linux-gnu/libc-2.15.so
b767e000-b7680000 r--p 0019f000 08:01 394145     
/lib/i386-linux-gnu/libc-2.15.so
b7680000-b7681000 rw-p 001a1000 08:01 394145     
/lib/i386-linux-gnu/libc-2.15.so
b7681000-b7685000 rw-p 00000000 00:00 0 
b7685000-b769c000 r-xp 00000000 08:01 394225     
/lib/i386-linux-gnu/libpthread-2.15.so
b769c000-b769d000 r--p 00016000 08:01 394225     
/lib/i386-linux-gnu/libpthread-2.15.so
b769d000-b769e000 rw-p 00017000 08:01 394225     
/lib/i386-linux-gnu/libpthread-2.15.so
b769e000-b76a0000 rw-p 00000000 00:00 0 
b76a0000-b76d4000 r-xp 00000000 08:01 1067215    /usr/lib/libsphinxbase.so.1.0.0
b76d4000-b76d5000 r--p 00033000 08:01 1067215    /usr/lib/libsphinxbase.so.1.0.0
b76d5000-b76d6000 rw-p 00034000 08:01 1067215    /usr/lib/libsphinxbase.so.1.0.0
b76e7000-b76ea000 rw-p 00000000 00:00 0 
b76ea000-b76eb000 r-xp 00000000 00:00 0          [vdso]
b76eb000-b770b000 r-xp 00000000 08:01 394125     /lib/i386-linux-gnu/ld-2.15.so
b770b000-b770c000 r--p 0001f000 08:01 394125     /lib/i386-linux-gnu/ld-2.15.so
b770c000-b770d000 rw-p 00020000 08:01 394125     /lib/i386-linux-gnu/ld-2.15.so
bffb3000-bffd4000 rw-p 00000000 00:00 0          [stack]
Traceback (most recent call last):
  File "/usr/local/bin/vid", line 101, in <module>
    quiet=configuration.QUIET_MODE, thrd_n=multiprocessing.cpu_count() * 5)
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 919, in extract_speakers
    self.diarization()  # start diarization over your wave file
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 713, in diarization
    self._to_MFCC()
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 719, in _to_MFCC
    fm.extract_mfcc(self._basename)
  File "/usr/local/lib/python2.7/dist-packages/voiceid/fm.py", line 390, in extract_mfcc
    utils.start_subprocess(commandline)
  File "/usr/local/lib/python2.7/dist-packages/voiceid/utils.py", line 62, in start_subprocess
    raise e
OSError: Subprocess <subprocess.Popen object at 0xb700086c> closed unexpectedly 
[sphinx_fe -verbose no -mswav yes -i recordingaudio/hello3.wav -o 
recordingaudio/hello3.mfcc]


I have googled on the web about ubuntu regarding the buffer overflow problem. 
Some suggests to downgrade the gcc version but still cannot solve the problem 
after downgrading. Can you give me some suggestion?

What steps will reproduce the problem?
1. Try to start voiceidplayer

What is the expected output? What do you see instead?
The GUI to show up

What version of the product are you using? On what operating system?
Voiceid.02 for OSX 

Please provide any additional information below.
- Running OS X 10.8.4
- Python 2.7 32 bit
- Tried with mplayer and mplayer2

Stack Trace: 
$ voiceidplayer
['/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer']
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer", line 1145, in <module>
    app = App(sys.argv, redirect=False)
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer", line 1137, in __init__
    self.controller = Controller(self, cl_args)
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer", line 95, in __init__
    self.player = Player(self.frame)
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer", line 646, in __init__
    self.controlSizer = self.build_player_controls()
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer", line 728, in build_player_controls
    self.build_btn(btn, controlSizer)
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/voiceidplayer", line 710, in build_btn
    name=btnDict['name'])
  File "/usr/local/lib/wxPython-unicode-2.8.12.0/lib/python2.7/site-packages/wx-2.8-mac-unicode/wx/lib/buttons.py", line 404, in __init__
    self.SetBitmapLabel(bitmap)
  File "/usr/local/lib/wxPython-unicode-2.8.12.0/lib/python2.7/site-packages/wx-2.8-mac-unicode/wx/lib/buttons.py", line 441, in SetBitmapLabel
    image = wx.ImageFromBitmap(bitmap)
  File "/usr/local/lib/wxPython-unicode-2.8.12.0/lib/python2.7/site-packages/wx-2.8-mac-unicode/wx/_core.py", line 3473, in ImageFromBitmap
    val = _core_.new_ImageFromBitmap(*args, **kwargs)
wx._core.PyAssertionError: C++ assertion "Ok()" failed at 
/BUILD/wxPython-src-2.8.12.0/src/mac/carbon/bitmap.cpp(1360) in 
ConvertToImage(): invalid bitmap

TODO, unless this was caused by one of my patches.

Hi,

I'm trying to use voiceid for speaker recognition, identifying speakers in 
recordings of the Colorado House of Representatives and Senate. Thanks for the 
library. I know it represents a ton of work. I have everything setup and 
running on a Ubuntu ec2 instance. I've recently started getting the following 
error when trying to identify with previously created voice models:

Traceback (most recent call last):
  File "/usr/lib/python2.7/threading.py", line 810, in __bootstrap_inner
    self.run()
  File "/usr/lib/python2.7/threading.py", line 763, in run
    self.__target(*self.__args, **self.__kwargs)
  File "/home/lkacenjar/test/voiceid/db.py", line 477, in __match_voice
    out[speakerkey] = self.match_voice(wave_file, speaker, gender)
  File "/home/lkacenjar/test/voiceid/db.py", line 376, in match_voice
    gender + '.' + identifier + '.gmm', cls)
  File "/home/lkacenjar/test/voiceid/sr.py", line 1422, in manage_ident
    idx = line.index('score:' + speaker) + len('score:' + speaker + " = ")
ValueError: substring not found

If I wrap line 1422-1427 in a try/catch it finishes, but then makes no matches. 
What can I do to get this working? Thanks.

What steps will reproduce the problem?
I only did 4 lines of codes, and it just stops responding after I tried doing 
the "db.add_model" command.

Codes:

from voiceid.sr import Voiceid
from voiceid.db import GMMVoiceDB
db = GMMVoiceDB('C:\\Users\\IdaLim\\Desktop\\trainmusic')
db.add_model('testrecord', 'ida')
#print db.get_speakers()

What is the expected output? What do you see instead?
I expected to see some response from the program. I tried doing the 
db.get_speakers() command, but there's no output too.


What version of the product are you using? On what operating system?
I'm using python 2.7.8 32bit, on a windows 7 64bit OS. If I'm not wrong, I'm 
using voiceid 0.2.

Skip diarization in build_gmm

Hi, I think I have properly installed the setup.py on window 7.

After I have got every dependencies installed, and type "python setup.py 
install", I've got the following response:
running install
running build
running build_py
running build_scripts
running install_lib
running install_scripts
running install_data
running install_egg_info
....
Writing C:/Python26/Lib/site-packages/voieid-0.1-py2.6.egg-info


However, when I try to use your example (located under using library..wiki 
page), error occurs..

Trackback 
from voiceid.sr import Voiceid
 File src\voiceid\__init__.py line 119, in module
output_redirect = open('/dev/'null','w')
IOError: [Errno 2] No such file or directory: '/dev/null'

Please help.

I have successfully solved the previous dependencies problem.

I think the problem comes from db.add_model('recordingaudio/joeyyung', 'agnes', 
'F')

But when I run your example sources, I got the following response:


Traceback (most recent call last):
  File "/home/lee/workspace/voiceid/src/src/voiceidimplementation.py", line 12, in <module>
    db.add_model('recordingaudio/joeyyung', 'agnes', 'F')
  File "/home/lee/workspace/voiceid/src/src/voiceid/db.py", line 178, in add_model
    fm.build_gmm(basefilename, identifier)
  File "/home/lee/workspace/voiceid/src/src/voiceid/fm.py", line 306, in build_gmm
    _train_map(filebasename)
  File "/home/lee/workspace/voiceid/src/src/voiceid/fm.py", line 690, in _train_map
    utils.start_subprocess(commandline)
  File "/home/lee/workspace/voiceid/src/src/voiceid/utils.py", line 67, in start_subprocess
    raise err
OSError: Subprocess <subprocess.Popen object at 0xb75ce8ac> closed unexpectedly 
[java -Xmx256m -cp /usr/local/share/voiceid/LIUM_SpkDiarization-4.22.jar 
fr.lium.spkDiarization.programs.MTrainMAP --sInputMask=%s.ident.seg 
--fInputMask=%s.mfcc --fInputDesc=audio16kHz2sphinx,1:3:2:0:0:0,13,1:1:300:4 
--tInputMask=%s.init.gmm --emCtrl=1,5,0.01 --varCtrl=0.01,10.0 
--tOutputMask=%s.gmm recordingaudio/joeyyung]


Please help`~

Hello, last time I have already ask the problem about the youtube video. This 
time I have svn up to the lastest version 190. However, when I import the mp4 
file downloaded from youtube at the menu  File > Open Video inside 
voiceidplayer, I get the error message at terminal:  
MplayerCtrl.BuildProcessError: [Errno 2] No such file or directory
I would like to know is it a bug? Can you tell me it it supposed to have a 
video screen being shown on the voiceidplayer when opening any video file?

I have svn up to the latest version. Now, I can sucessfully add model to the 
database and undergo voice matching. But, I soon discover some wav file cannot 
produce a gmm file when undergoing db.add_model. I guess, is it because of the 
sampling rate or anything else that contribute to success or failure despite 
the same wav file format of source? Can you tell me what kind of wav file is 
likely successful? 

What steps will reproduce the problem?
1. Run vid -i RIFF-little-endian-16bit-8kh-wave-file.wav

Error: Traceback (most recent call last):
  File "/usr/local/bin/vid", line 132, in <module>
    thrd_n=multiprocessing.cpu_count() * 5)
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 899, in extract_speakers
    self._to_wav()
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 605, in _to_wav
    fm.file2wav(self.get_filename())
  File "/usr/local/lib/python2.7/dist-packages/voiceid/fm.py", line 93, in file2wav
    + "wavenc ! filesink location=" + name + ".wav ")
  File "/usr/local/lib/python2.7/dist-packages/voiceid/utils.py", line 67, in start_subprocess
    raise err
OSError: Subprocess <subprocess.Popen object at 0xb7490c2c> closed unexpectedly 
[gst-launch filesrc location='/opt/resources/silence.wav' ! decodebin ! 
audioresample ! 'audio/x-raw-int,rate=16000' ! audioconvert ! 
'audio/x-raw-int,rate=16000,depth=16,signed=true,channels=1' !wavenc ! filesink 
location= RIFF-little-endian-16bit-8kh-wave-file.wav]

What is the expected output? What do you see instead?
Expected: It should work with 8kHz sampled wave files as well. Or atleast give 
an exception that the file doesn't match the sampling rate.. and exits.
Actual: it gives an exception, doesn't exit cleanly and truncates the input 
wave file!

What version of the product are you using? On what operating system?
Revision: 189. URL: http://voiceid.googlecode.com/svn/trunk
Ubuntu 12.04 32bit wheezy/sid

To reproduce:

OS: Crunchbang 11 Waldorf 64-bit
Python 2.7

Run the following:

    from voiceid.sr import Voiceid
    from voiceid.db import GMMVoiceDB

    db = GMMVoiceDB('/home/gavin/.voiceid/gmm_db')
    print 'adding maps0 audio'
    db.add_model('/home/gavin/maps0_002', 'maps0')


The following error is thrown:

Traceback (most recent call last):
line type: <type 'str'>
  File "/home/gavin/PycharmProjects/transcription/audio/voiceid-test.py", line 11, in <module>
    db.add_model('/home/gavin/maps0_002', 'maps0')
  File "/usr/local/lib/python2.7/dist-packages/voiceid/db.py", line 249, in add_model
    if abs(abs(float(line[idx:iidx])) - abs(score)) < 0.07:
TypeError: bad operand type for abs(): 'NoneType'

The type of score is None. I can pass in a value for score, but I don't know 
what it should be.

On Ubuntu 12.04, the snippet runs without errors, even when I do not pass in a 
value for score.

Thanks,
Gavin

What steps will reproduce the problem?
1. Use not PCM16 wav file as input for model creation 
2. vid -s test -g test_not_PCM16.wav


What is the expected output? What do you see instead?

[FeatureSet] read : compute data test java.lang.IllegalArgumentException: 
Unsupported conversion: PCM_SIGNED 16000.0 Hz, 16 bit, mono, 2 bytes/frame, 
big-endian from PCM_SIGNED 44100.0 Hz, 16 bit, stereo, 4 bytes/frame, 
little-endian
    at javax.sound.sampled.AudioSystem.getAudioInputStream(AudioSystem.java:955)
    at fr.lium.spkDiarization.libFeature.FeatureFactory.getAudio(FeatureFactory.java:161)
    at fr.lium.spkDiarization.libFeature.FeatureFactory.MakeFeature(FeatureFactory.java:191)
    at fr.lium.spkDiarization.libFeature.FeatureFactory.MakeMFCCFeature(FeatureFactory.java:234)
    at fr.lium.spkDiarization.libFeature.FeatureSet.read(FeatureSet.java:740)
    at fr.lium.spkDiarization.libFeature.FeatureSet.setCurrentShow(FeatureSet.java:1091)
    at fr.lium.spkDiarization.system.Diarization.ester2Version(Diarization.java:310)
    at fr.lium.spkDiarization.system.Diarization.main(Diarization.java:540)

What version of the product are you using? On what operating system?

Latest trunk, Mac OX X 10.7.4

Please provide any additional information below.

The problem is that fm.py:file2wav converts source input (test.wav) to 
test_.wav and then
test._wav is not used for later diarization. The solution could be in renaming 
source file before conversation
to e.g. test_orig.wav and then save conversation result with name of initial 
source file name e.g. test.wav

Matching voice with only same gender gmm 

What steps will reproduce the problem?
1. use any of the get_gender functions
2. provide a file with noise or silence

What is the expected output? What do you see instead?
Expected output: Gender : U
Actual output:   Gender : F

What version of the product are you using? On what operating system?
Ubuntu 12.04. Revision 192

Please provide any additional information below.
Sample audio file attached.

If I extract the folder LIUM_SpkDiarization-4.7.jar given in share folder and 
then compress it back using export from eclipse, install the setup again, the 
code stops working and gives the following error :

OSError: Subprocess <subprocess.Popen object at 0x7f63576588d0> closed 
unexpectedly [java -Xmx2048m -jar 
/usr/local/share/voiceid/LIUM_SpkDiarization-4.7.jar 
fr.lium.spkDiarization.system.Diarization --fInputMask=%s.wav 
--sOutputMask=%s.seg --doCEClustering s27]


Using voiceid-0.2 in Ubuntu-12.04

Code runs successfully but once extract LIUM_SpkDiarization-4.7.jar and 
compress back again into .jar , it stops working.Can you please help on what 
method to use for compressing?

Hi,

I recently switched to Ubuntu 13.10. After installing the Voiceid, I tested my 
samples following the the few codes given for usage on the installation page. 
Some samples were diarized while others were not. I don't know why.

I however, proceeded to trying out the library. When I get to the add_model to 
create/train my voices in the database, it seems to hang or take forever. I am 
stuck at this point. Any help will be appreciated. 

What steps will reproduce the problem?
In the Windows Command Prompt, enter the following commands:
1. python vid -s speaker1 -g training.wav
2. python vid -i testing.wav -f json

What is the expected output? What do you see instead?

In testing.json, "speaker1" should show up as one of the speaker candidates. 
However, the recognition was done as if there was no model in the database. The 
same data and procedure generate correct results under Mac OS X.

What version of the product are you using? On what operating system?

Both v0.3 and the latest from the trunk. OS is Win 8.1.

Please provide any additional information below.

Please let me know if there is way to make it work. Thanks!

Hi,
I am using windows 7. I followed your library through but when I reached the # 
print the clusters (one for every speaker) and relative speakers' names; I get 
the following error and can’t figure out which two arguments. Any advice?
for c in v.get_cluster():
    cluster = v.get_cluster(c)
    print cluster
    cluster.print_segments()
    print

Traceback (most recent call last):
  File "<pyshell#24>", line 1, in <module>
    for c in v.get_cluster():
TypeError: get_cluster() takes exactly 2 arguments (1 given)

Use attached patches. Summary:

#1
* Generate .cmd wrappers during distutils' install_scripts phase
* Substitute ";" with "&&" which works in both cmd.exe and bash/sh

#2
* Switch to distutils.command.install_scripts.install_scripts.make_file,
  which handles timestamp checking
* Switch to distutils.file_util.write_file
* Fix: Add .cmd wrapper scripts to the intalled-files.txt manifest

Hi,

I'm trying to process an audio file but I always get the same error:  "IOError: 
File test_voices_.i.seg empty"
The audio file is PCM16, I'm using ubuntu 12.10, and I have replaced the 
sphinxbase-utils 0.4.1-0ubuntu4 package for this one: sphinxbase-utils 
0.4.1-0ubuntu1


adanancamil@ubuntu:~/Documents$ vid -i test_voices.wav
test_voices.wav
converting_file
test_voices_.wav
diarization
Traceback (most recent call last):
  File "/usr/local/bin/vid", line 133, in <module>
    thrd_n=multiprocessing.cpu_count() * 5)
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 944, in extract_speakers
    self.diarization()  # start diarization over your wave file
  File "/usr/local/lib/python2.7/dist-packages/voiceid/sr.py", line 730, in diarization
    str(self._diar_conf[1]))
  File "/usr/local/lib/python2.7/dist-packages/voiceid/fm.py", line 590, in diarization
    utils.ensure_file_exists(filebasename + '.i.seg')
  File "/usr/local/lib/python2.7/dist-packages/voiceid/utils.py", line 101, in ensure_file_exists
    raise IOError("File %s empty" % filename)
IOError: File test_voices_.i.seg empty


what am I doing wrong? 
Could you please help me?

Thanks in advance!
regards from Chile
Adan

Simple program to test...

from voiceid.sr import Voiceid
from voiceid.db import GMMVoiceDB

db = GMMVoiceDB('db')

db.add_model('person1', 'John')

print db.get_speakers()

exit
v = Voiceid(db, 'test.wav')

v.extract_speakers()

for c in v.get_clusters():
  cluster = v.get_cluster(c)
  print cluster
  cluster.print_segments()
  print

gst-launch --version
gst-launch-0.10 version 0.10.29
GStreamer 0.10.29
http://download.fedora.redhat.com/fedora


Traceback (most recent call last):
  File "test.py", line 13, in <module>
    v.extract_speakers()
  File "/usr/local/lib/python2.7/site-packages/voiceid/sr.py", line 925, in extract_speakers
    self._to_wav()
  File "/usr/local/lib/python2.7/site-packages/voiceid/sr.py", line 635, in _to_wav
    fname = fm.file2wav(self.get_filename())
  File "/usr/local/lib/python2.7/site-packages/voiceid/fm.py", line 84, in file2wav
    + "wavenc ! filesink location=" + name + ".wav ")
  File "/usr/local/lib/python2.7/site-packages/voiceid/utils.py", line 76, in start_subprocess
    raise err
OSError: Subprocess <subprocess.Popen object at 0x7fcf5506c150> closed 
unexpectedly [gst-launch filesrc location='test.wav' ! decodebin ! 
audioresample ! 'audio/x-raw-int,rate=16000' ! audioconvert ! 
'audio/x-raw-int,rate=16000,depth=16,signed=true,channels=1' !wavenc ! filesink 
location=test_.wav ]

What steps will reproduce the problem?
1. Start from cmd.exe without any arguments.


What is the expected output? What do you see instead?
GUI fails to initialize. Endless loop of "Exception RuntimeError: 'maximum 
recursion depth exceeded'"


What version of the product are you using? On what operating system?
* Windows 7
* Python 2.7.5.6
* wxPython 2.9.5.0

Details
I opened a thread on the wxPython-users mailing list 
@https://groups.google.com/forum/#!topic/wxpython-users/7hA7ZXXMx20. The 
suggestions there fix the problem, though I can't be sure because the UI 
continues to randomly lock-up for short intervals quite often. While this is 
probably a different issue, it means I can't comprehensively test the following 
summarized solutions:

#1: get rid of ClusterList.on_size, use built-in auto-layout
ClusterList.__init__
...     
        #self.Bind(wx.EVT_SIZE, self.on_size)
        #self.info.Bind(wx.EVT_SIZE, self.on_size)
        #self.list.Bind(wx.EVT_SIZE, self.on_size)
...
ClusterList.on_size
    #def on_size(self, event):
    #    """Update layouts on size event"""
    #    self.list.Refresh()
    #    self.list.Layout()
    #    self.info.Refresh()
    #    self.info.Layout()
    #    self.Refresh()
    #    self.Layout()

#2: 
ClusterList.__init__
...
        self.Bind(wx.EVT_SIZE, self.on_size_self)
        self.info.Bind(wx.EVT_SIZE, self.on_size_special)
        self.list.Bind(wx.EVT_SIZE, self.on_size_special)
...
ClusterList.on_size*
    def on_size_self(self, event):
        """Update layouts on size event"""
        self.list.Refresh()
        self.list.Layout()
        self.info.Refresh()
        self.info.Layout()
        self.Refresh()
        self.Layout()
        event.Skip()

    def on_size_special(self, event):
        """Under no circusmtances call self.Layout(), will case *massive* problems"""
        pass

What is the expected output?

Did your program support Ivector based speaker identification?

What steps will reproduce the problem?
1. start vid on command line

What is the expected output? What do you see instead?
Verification that software is installed correctly.
Received an error instead.

What version of the product are you using? On what operating system?
Voiceid .2
Python 2.7

Please provide any additional information below.

Voiceid is referencing an incorrect pathway. 
- the wrong pathway Voiceid is trying to access: 
/Library/Frameworks/Python.framework/Versions/2.7/local/share/voiceid/
- the correct pathway is: 
/Library/Frameworks/Python.framework/Versions/2.7/share/voiceid/


Traceback: 
$ vid
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/2.7/bin/vid", line 126, in <module>
    utils.check_deps()
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/voiceid/utils.py", line 132, in check_deps
    ensure_file_exists(CONFIGURATION.LIUM_JAR)
  File "/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/voiceid/utils.py", line 102, in ensure_file_exists
    % filename)
IOError: File 
/Library/Frameworks/Python.framework/Versions/2.7/local/share/voiceid/LIUM_SpkDi
arization-4.7.jar doesn't exist or not correctly created

1.I am trying to add a voice model for file s2_new.wav. I give the following 
command:

python scripts /vid -j "C:\Python27\share\voiceid\LIUM_SpkDiarization-4.7.jar" 
-b "C:\Python27\share\voiceid\ubm.gmm" -s "testing1" -g 
"C:\Pytho27\pdtrain\s2_new.wav"

I get the following error:
File C:\Python27\pdtrain\s2_new_flt.3.seg empty

I see that s2_new_flt.3.seg has been created but is 0 in size. I also see other 
intermediator files like .adj.3.seg, .c.gmm, .d.3.gmm, etc created and all 
these are not 0 in size.

Can you please tell me on why flt.3.seg is being created as empty file and 
hence adding voice model is not working. I am attaching the input s2_new.wav. 
s2_new.wav has following properties - (1,2,16000, 17368, 'NONE", 'not 
compressed')


thanks a lot,
Regards,
Priy Dixit

After running `vid -i test.mp3 -u` for 35 minutes, it crashes with the 
exception:

    Traceback (most recent call last):
      File "/usr/local/project/.env/bin/vid", line 138, in <module>
        thrd_n=multiprocessing.cpu_count() * 5)
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/sr.py", line 1003, in extract_speakers
        start_time)
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/sr.py", line 1010, in _cluster_matching
        self._match_clusters(interactive, quiet)
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/sr.py", line 837, in _match_clusters
        clu, speakers[clu])
      File "/usr/local/project/.env/local/lib/python2.7/site-packages/voiceid/sr.py", line 1486, in _interactive_training
        " name\n Press enter to skip\n> ")
    ValueError: I/O operation on closed file