This code is 100x faster:

[jitsi]

This code is 100x faster:

[DevZiegler]

The WER is defined as follows:

See also here: Word error rate WIkipedia

Your code would have to be adapted like this:
return Levenshtein.distance(''.join(w1), ''.join(w2))/float(len(w1))

[nikvaessen]

For people confused about the import: pip install python-Levenshtein

[buriy]

@DevZiegler I only showed the way to make the code faster.
Complete the code at your own.

[nikvaessen]

Current benchmark:

executing wer with 1 sentences:
	mean=0.0003 sec std=0.0000 sec
executing wer with 10 sentences:
	mean=0.0134 sec std=0.0006 sec
executing wer with 50 sentences:
	mean=0.3261 sec std=0.0024 sec
executing wer with 100 sentences:
	mean=1.3144 sec std=0.0046 sec

[nikvaessen]

Your code:

executing wer with 1 sentences:
	mean=0.0000 sec std=0.0000 sec
executing wer with 10 sentences:
	mean=0.0001 sec std=0.0000 sec
executing wer with 50 sentences:
	mean=0.0022 sec std=0.0001 sec
executing wer with 100 sentences:
	mean=0.0079 sec std=0.0002 sec

[gabrielziegler3]

Although this solution is indeed much faster, it adds a C++ dependency. It would be nice if there was the possibility to use the old wer calculation without this dependency, maybe an option to choose wether to use C-level Levenshtein module or not.

[nikvaessen]

Would you be able to share your scenario where the dependency of python-Levenstein is prohibitive?

…

On 26/05/2021 16:09, Gabriel Ziegler wrote: Although this solution is indeed much faster, it adds a C++ dependency. It would be nice if there was the possibility to use the old wer calculation without this dependency, maybe an option to choose wether to use C-level Levenshtein module or not. — You are receiving this because you modified the open/close state. Reply to this email directly, view it on GitHub <#7 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ABXEFA524KVNADNIXOOJMVDTPT6H5ANCNFSM4HAVTDVA>.

[gabrielziegler3]

In an environment where C++ dependencies' installation are blocked because they are installed at system-level, but pip packages are enabled for instance. Does it make sense?

In such a case, the following error is raised because I don't have C++ dependencies.

Complete output (27 lines):
  running bdist_wheel
  running build
  running build_py
  creating build
  creating build\lib.win32-3.8
  creating build\lib.win32-3.8\Levenshtein
  copying Levenshtein\StringMatcher.py -> build\lib.win32-3.8\Levenshtein
  copying Levenshtein\__init__.py -> build\lib.win32-3.8\Levenshtein
  running egg_info
  writing python_Levenshtein.egg-info\PKG-INFO
  writing dependency_links to python_Levenshtein.egg-info\dependency_links.txt
  writing entry points to python_Levenshtein.egg-info\entry_points.txt
  writing namespace_packages to python_Levenshtein.egg-info\namespace_packages.txt
  writing requirements to python_Levenshtein.egg-info\requires.txt
  writing top-level names to python_Levenshtein.egg-info\top_level.txt
  reading manifest file 'python_Levenshtein.egg-info\SOURCES.txt'
  reading manifest template 'MANIFEST.in'
  warning: no previously-included files matching '*pyc' found anywhere in distribution
  warning: no previously-included files matching '*so' found anywhere in distribution
  warning: no previously-included files matching '.project' found anywhere in distribution
  warning: no previously-included files matching '.pydevproject' found anywhere in distributi
on
  writing manifest file 'python_Levenshtein.egg-info\SOURCES.txt'
  copying Levenshtein\_levenshtein.c -> build\lib.win32-3.8\Levenshtein
  copying Levenshtein\_levenshtein.h -> build\lib.win32-3.8\Levenshtein
  running build_ext
  building 'Levenshtein._levenshtein' extension
  error: Microsoft Visual C++ 14.0 or greater is required. Get it with "Microsoft C++ Build T
ools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
  ----------------------------------------
  ERROR: Failed building wheel for python-Levenshtein

My workaround was to checkout wer function to commit 2f1daee that is right before the Levenshtein implementation