Python API for Romanian diacritics restoration
Project description
RO Diacritics module
RO Diacritics is a straightforward diacritics restoration module for Romanian Language
from ro_diacritics import restore_diacritics
print(restore_diacritics("fara poezie, viata e pustiu"))
or correcting a pandas dataframe:
from ro_diacritics import restore_diacritics
df['text-diacritice'] = df['text'].apply(restore_diacritics)
Installing
$ python -m pip install ro-diacritics
or
$ pip install ro-diacritics
Requirements
- torch and torchtext
- numpy
- nltk and scikit-learn (for training)
- needs nltk.download('punkt') for tokenization
References
- Ruseti, S., Cotet, T. M., & Dascalu, M. (2020). Romanian Diacritics Restoration Using Recurrent Neural Networks. arXiv preprint arXiv:2009.02743.
- https://github.com/teodor-cotet/DiacriticsRestoration
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
ro-diacritics-0.9.4.2.tar.gz
(12.5 kB
view details)
File details
Details for the file ro-diacritics-0.9.4.2.tar.gz
.
File metadata
- Download URL: ro-diacritics-0.9.4.2.tar.gz
- Upload date:
- Size: 12.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.9.16
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 92bffa40355c4120b10354b783c8950c82d48da005757546cf86c00894a3e321 |
|
MD5 | cf4ab9868049a2a2e3bcf9f28a3d0d5b |
|
BLAKE2b-256 | b41f8c4f370f9ea7c229f6a5d54678fed1002acc3e7adb8bf895e3aa934211db |