speechio/chinese_text_normalization

Chinese text normalization for speech processing

51
/ 100
Established

This project helps speech processing professionals prepare Chinese text for automatic speech recognition (ASR) systems. It takes raw Chinese text, which might include numbers, dates, and non-standard words, and converts them into their spoken-word equivalents. The output is clean, normalized Chinese text that's ready for ASR model training or inference, making it useful for ASR engineers and researchers.

722 stars. No commits in the last 6 months.

Use this if you need to transform raw Chinese text containing numbers, dates, or other non-standard words into their fully written-out, spoken forms for an automatic speech recognition pipeline.

Not ideal if your primary need is for text normalization in languages other than Chinese, or if you require advanced, AI-model-based text normalization beyond rule-based transformations.

speech-recognition ASR-data-preparation Chinese-language-processing text-pre-processing natural-language-understanding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

722

Forks

150

Language

Python

License

MIT

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.