Evaluating ASR (automatic speech recognition) hypotheses, i.e. computing word error rate.
Python module for evaluting ASR hypotheses (i.e. word error rate and word recognition rate).
This module depends on the editdistance project, for computing edit distances between arbitrary sequences.
The formatting of the output of this program is very loosely based around the same idea as the align.c program commonly used within the Sphinx ASR community. This may run a bit faster if neither instances nor confusions are printed.
Please let me know if you have any comments, questions, or problems.
The easiest way to install is using pip:
pip install asr-evaluation
Alternatively you can clone this git repo and install using distutils:
git clone firstname.lastname@example.org:belambert/asr-evaluation.git cd asr-evaluation python setup.py install
To uninstall with pip:
pip uninstall asr-evaluation
For command line usage, see:
python bin/evaluate.py --help
It should be something like this:
usage: evaluate.py [-h] [-i] [-id] [-c] [-p] [-m count] [-a] [-e] ref hyp Evaluate an ASR transcript against a reference transcript. positional arguments: ref Reference transcript filename hyp ASR hypothesis filename optional arguments: -h, --help show this help message and exit -i, --print-instances Print the individual sentences and their errors -id, --has-ids Hypothesis and reference files have ids in the last token? -c, --confusions Print tables of which words were confused -p, --print-wer-vs-length Print table of average WER grouped by reference sentence length -m count, --min-word-count count Minimum word count to show a word in confusions -a, --case-insensitive Down-case the text before running the evaluation. -e, --remove-empty-refs Skip over any examples where the reference is empty.