A small package that convert time, cardinal numbers, some acronyms and transliterations cases from their written form to their verbalized form. It can be used to normalize text before feeding it into a text-to-speech model.
Project description
Kinya_TN
Kinyarwanda_TextNormalization(Kinya_TN) is a small package that convert time, cardinal numbers, some acronyms and transliterations cases from their written form to their verbalized form. It can be used to preprocess text to an adequate form for text-to-speech models.
Installation
pip install kinya_tn
Usage
from kinya_tn import text_normalization
text_normalization.normalize("abantu 2000 baje kure ikiganiro cya covid cyatangiye 12:40")
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
kinya_tn-0.0.1.3.1.tar.gz
(233.1 kB
view hashes)
Built Distribution
kinya_tn-0.0.1.3.1-py3-none-any.whl
(246.7 kB
view hashes)
Close
Hashes for kinya_tn-0.0.1.3.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 02a744acbc1f12f8f412922c1861361fee3f5a47a697e572331036dd147cb25d |
|
| MD5 | 90f76b1013e4f8822283cc3b209630b6 |
|
| BLAKE2b-256 | 13668754ceea408e1719a957fd0883b087a7239997a34fe223d6e7d51b2bf367 |
