speechio/chinese_text_normalization
Chinese text normalization for speech processing
Handles multiple non-standard word (NSW) categories—cardinals, dates, fractions, money, percentages, and phone numbers—converting them to spoken forms for ASR pipelines. Built with regex-based normalizers in Python and finite-state grammars in Thrax, it supports multiple input formats (plain text, Kaldi archives, TSV tables) and includes punctuation removal with language-specific rules. Designed specifically for Chinese speech processing workflows rather than as a generic NLP framework.
722 stars. No commits in the last 6 months.
Stars
722
Forks
150
Language
Python
License
MIT
Category
Last pushed
Mar 18, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/speechio/chinese_text_normalization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
NickZaitsev/ru-normalizr
ru-normalizr — лучший open-source нормализатор русского текста. Приводит числа, даты, время,...
repodiac/german_transliterate
Python module to clean and transliterate (i.e. normalize) German text including abbreviations,...
gladiaio/normalization
A lightweight library for normalizing speech transcripts before computing WER
google-research-datasets/TextNormalizationCoveringGrammars
Covering grammars for English and Russian text normalization
34j/mecab-text-cleaner
Simple Python package (CLI/Python API) for getting japanese readings (yomigana) and accents using MeCab.