Metadata-Version: 2.1
Name: vinorm
Version: 2.0.4
Summary: Python package for text normalization, use for frontend of Text-to-speech Reseach
Home-page: https://github.com/NoahDrisort/vinorm
Author: AILAB
Author-email: donhanbentre@gmail.com
License: AILAB
Description: Install ViNorm package
        ```
        pip install vinorm
        ```
        Using in python script
        ```python
        from vinorm import TTSnorm
        S=TTSnorm("Hàm này được phát triển từ 8/2019. Có phải tháng 12/2020 đã có vaccine phòng ngừa Covid-19 xmz ?")
        ```
        Some option
        ```python
        TTSnorm(text, punc = False, unknown = True, lower = True, rule = False )
        ```
        - **lower**: If true, get normalization with lowercase
        - **rule**: If true, just get normalization wit Regex, not using Dictionary Checking (this flag is not used with another flag)
        - **punc**: If true, do not replace punctuation with dot and coma
        - **unknown**: If true, replace unknown word, discard word undefine and do not contain vowel, do not spell word with vowel
        
        From version 2.0, do not replace unknown words, skip them for espeak handle in phonetization step
        - This version does not parse case: "Tổ chức WTO"
        WTO do not in dictionary -> unknow -> keep origin, do not spell as in version 1.0, this aim to use with espeak, let espeak handle, but the drawback is the output of espeak for this case is "ve1kɛɜpte1ɔ7", it does not split each syllable.
        - For new entity, need to update in the dictionary
        
        For update lastest version access: https://github.com/NoahDrisort/vinorm
        
        For version 1.0: spell words that is unknow by each character, check previous commit
        
        For C++ version: https://github.com/NoahDrisort/vinorm_cpp_version
        
        ### Update pypi
        ```sh
        python setup.py sdist bdist_wheel
        twine upload dist/*
        ```
Platform: UNKNOWN
Classifier: Development Status :: 4 - Beta
Classifier: License :: Free for non-commercial use
Classifier: Natural Language :: Vietnamese
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: C++
Classifier: Programming Language :: Python :: 3.6
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Description-Content-Type: text/markdown
