forked from Lainports/freebsd-ports
misc/py-jiwer: New port: Evaluate speech-to-text system with similarity measures
This commit is contained in:
parent
d5bf0a77eb
commit
219e72a7c3
4 changed files with 45 additions and 0 deletions
|
|
@ -439,6 +439,7 @@
|
|||
SUBDIR += py-icoextract
|
||||
SUBDIR += py-instructor
|
||||
SUBDIR += py-ipyfastscape
|
||||
SUBDIR += py-jiwer
|
||||
SUBDIR += py-kartograph
|
||||
SUBDIR += py-laspy
|
||||
SUBDIR += py-lazrs
|
||||
|
|
|
|||
29
misc/py-jiwer/Makefile
Normal file
29
misc/py-jiwer/Makefile
Normal file
|
|
@ -0,0 +1,29 @@
|
|||
PORTNAME= jiwer
|
||||
#DISTVERSIONPREFIX= v
|
||||
DISTVERSION= 3.0.4 # see https://github.com/jitsi/jiwer/issues/91
|
||||
CATEGORIES= misc python # machine-learning
|
||||
MASTER_SITES= PYPI # no tests
|
||||
PKGNAMEPREFIX= ${PYTHON_PKGNAMEPREFIX}
|
||||
|
||||
MAINTAINER= yuri@FreeBSD.org
|
||||
COMMENT= Evaluate speech-to-text system with similarity measures
|
||||
WWW= https://github.com/jitsi/jiwer
|
||||
|
||||
LICENSE= APACHE20
|
||||
LICENSE_FILE= ${WRKSRC}/LICENSE
|
||||
|
||||
BUILD_DEPENDS= ${PYTHON_PKGNAMEPREFIX}poetry-core>0:devel/py-poetry-core@${PY_FLAVOR}
|
||||
RUN_DEPENDS= ${PYTHON_PKGNAMEPREFIX}click>=8.1.3:devel/py-click@${PY_FLAVOR} \
|
||||
${PYTHON_PKGNAMEPREFIX}rapidfuzz>=3:devel/py-rapidfuzz@${PY_FLAVOR}
|
||||
|
||||
USES= python
|
||||
USE_PYTHON= pep517 concurrent autoplist #pytest
|
||||
|
||||
#USE_GITHUB= yes
|
||||
#GH_ACCOUNT= jitsi
|
||||
|
||||
TEST_ENV= ${MAKE_ENV} PYTHONPATH=${STAGEDIR}${PYTHONPREFIX_SITELIBDIR}
|
||||
|
||||
NO_ARCH= yes
|
||||
|
||||
.include <bsd.port.mk>
|
||||
3
misc/py-jiwer/distinfo
Normal file
3
misc/py-jiwer/distinfo
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
TIMESTAMP = 1722887112
|
||||
SHA256 (jiwer-3.0.4.tar.gz) = 2438acdc7ca22128fcab4be60db595809d2b5e73785b736de36dc3281a2a6ae8
|
||||
SIZE (jiwer-3.0.4.tar.gz) = 17515
|
||||
12
misc/py-jiwer/pkg-descr
Normal file
12
misc/py-jiwer/pkg-descr
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
JiWER is a simple and fast python package to evaluate an automatic speech
|
||||
recognition system. It supports the following measures:
|
||||
* word error rate (WER)
|
||||
* match error rate (MER)
|
||||
* word information lost (WIL)
|
||||
* word information preserved (WIP)
|
||||
* character error rate (CER)
|
||||
|
||||
These measures are computed with the use of the minimum-edit distance between
|
||||
one or more reference and hypothesis sentences. The minimum-edit distance is
|
||||
calculated using RapidFuzz, which uses C++ under the hood, and is therefore
|
||||
faster than a pure python implementation.
|
||||
Loading…
Add table
Reference in a new issue