iTRANSLIT is a deep learning based transliteration package for indic language
Project description
iTRANSLIT
iTRANSLIT is a deep learning based transliteration package for indic language
Installation
pip install itranslit
Dependency
pytorch 1.7.0 or 1.7.0+
NB: No GPU
need. It's CPU
based.
Supported Language and Language Code
Language Name | Langauage Code |
---|---|
Bangla | bn |
Gujarati | gu |
Hindi | hi |
Punjabi | pa |
Sindhi | sd |
Urdu | ur |
Malayalam | ml |
Tamil | ta |
API
from itranslit import Translit
translit = Translit('bn')
word = "aami"
output = translit.predict(word, topk=10)
print(output)
Datasets and Training Details
- We used Google Dakshina Dataset
- Thanks to AI4Bharat for providing training notebook with details explanation
- We trained Google Dakshina lexicons train datasets for 10 epochs with batch size 128, 1e-3, embedding dim = 300, hidden dim = 512, lstm, used attention
- We evaluated our trained model with Google Dakshina lexicon test data using AI4Bharat evaluation script
- You can find evaluation summary here
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
itranslit-1.0.1.tar.gz
(10.8 kB
view hashes)
Built Distribution
itranslit-1.0.1-py3-none-any.whl
(10.1 kB
view hashes)
Close
Hashes for itranslit-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 42859e91e63ca2cb1fed6af58dd9f19f652a853f19dd6c3936081cd2da85951b |
|
MD5 | aaf84217d4d75498c6bdb83e5d0cf506 |
|
BLAKE2b-256 | 703342111db986b3b0cc258062b891f58cfc8a3c874b36482fb8b29ac662227d |