文件名称:fastwer:用于快速字字符错误率 (WERCER) 计算的 PyPI 包
文件大小:539KB
文件格式:ZIP
更新时间:2024-06-18 09:26:03
natural-language-processing speech-recognition speech-processing spoken-language-processing spoken-language-recognition
FastWER 用于快速字/字符错误率 (WER/CER) 计算的 PyPI 包 快速(cpp 实现) 句子级和语料库级 WER/CER 分数 安装 pip install pybind11 fastwer 例子 import fastwer hypo = [ 'This is an example .' , 'This is another example .' ] ref = [ 'This is the example :)' , 'That is the example .' ] # Corpus-Level WER: 40.0 fastwer . score ( hypo , ref ) # Corpus-Level CER: 25.5814 fastwer . score ( hypo , ref , char_level = True ) # Sentence-Leve
【文件预览】:
fastwer-master
----MANIFEST.in(66B)
----VERSION(5B)
----src()
--------fastwer.hpp(674B)
--------bindings.cpp(359B)
--------fastwer.cpp(2KB)
----LICENSE(1KB)
----setup.py(4KB)
----README.md(699B)
----tests()
--------__init__.py(0B)
--------basic.py(5KB)
--------data()
----.gitignore(86B)