awbcan / voiceid

Automatically exported from code.google.com/p/voiceid
0 stars 0 forks source link

I'm getting "File empty" error when trying the diarization process #12

Open GoogleCodeExporter opened 9 years ago

GoogleCodeExporter commented 9 years ago
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

Original issue reported on code.google.com by adan.anc...@gmail.com on 3 Apr 2013 at 2:13

GoogleCodeExporter commented 9 years ago
Hi,

if you did an update of the system after you install the right version of 
sphinxbase-utils, maybe it was updated too.
Ensure you have still installed the right version by typing `dpkg -s 
sphinxbase-utils`.
I just tried in Ubuntu 12.10 in virtualbox, I have this output:

Package: sphinxbase-utils
Status: install ok installed
Priority: optional
Section: sound
Installed-Size: 196
Maintainer: Ubuntu MOTU Developers <ubuntu-motu@lists.ubuntu.com>
Architecture: i386
Source: sphinxbase
Version: 0.4.1-0ubuntu1
Depends: libasound2 (>> 1.0.18), libc6 (>= 2.7), libsphinxbase1 (>= 0.4.1), perl
Description: Sphinx base libraries - utilities
 This package contains a number of utilities, such as sphinx_pitch,
 sphinx_fe and sphinx_lm_sort, which are useful for all Sphinx speech
 recognition engines.
Original-Maintainer: David Huggins-Daines <dhuggins@cs.cmu.edu>

For me everything works well, if still doesn't work, send me the wave you test.

Just a troubleshoot, for ubuntu 12.10 I had to install manually libsphinxbase1, 
otherwise the installation of sphinxbase-utils gave an error.
If you fall in this case type `sudo apt-get install libsphinxbase1.

Thanks for using voiceid! :-)
Greetings from Italy
Mauro

Original comment by maurome...@gmail.com on 4 Apr 2013 at 10:30

GoogleCodeExporter commented 9 years ago
I'll handle this one.

Original comment by maurome...@gmail.com on 4 Apr 2013 at 11:28

GoogleCodeExporter commented 9 years ago
Thanks you so much for your answer mate!   

I had installed the wrong version of sphinxbase-utils... I just fixed following 
your advice and now it's working properly!

btw, voiceid is awesome!

Cheers,
Adan

Original comment by adan.anc...@gmail.com on 4 Apr 2013 at 10:20

GoogleCodeExporter commented 9 years ago
My setup is

rutik@frutik-laptop:~/work/voiceid/data/test$ dpkg -s sphinxbase-utils
Package: sphinxbase-utils
Status: install ok installed
Priority: optional
Section: sound
Installed-Size: 196
Maintainer: Ubuntu MOTU Developers <ubuntu-motu@lists.ubuntu.com>
Architecture: i386
Source: sphinxbase
Version: 0.4.1-0ubuntu1
Depends: libasound2 (>> 1.0.18), libc6 (>= 2.7), libsphinxbase1 (>= 0.4.1), perl
Description: Sphinx base libraries - utilities
 This package contains a number of utilities, such as sphinx_pitch,
 sphinx_fe and sphinx_lm_sort, which are useful for all Sphinx speech
 recognition engines.
Original-Maintainer: David Huggins-Daines <dhuggins@cs.cmu.edu>

but still no luck

rutik@frutik-laptop:~/work/voiceid/data/test$ vid -i mr_arkadin.wav -u
mr_arkadin.wav
converting_file
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 mr_arkadin.i.seg empty

Original comment by fru...@gmail.com on 9 Apr 2013 at 6:40

GoogleCodeExporter commented 9 years ago
I can't reproduce your error. 
Are you using the package or the svn version?
I just tried the same command line with the same file using the package and svn 
version and it works for me.
Have you tried to listen to the wave, to ensure it is not corrupted?
What's your java version?
Ubuntu version?

Original comment by maurome...@gmail.com on 10 Apr 2013 at 10:07