Language identifier based on an LSTM model
Project description
*** Redistribution and use in source, with or without modifications, are permitted for academic purposes, provided that the proper acknowledgements are done.
##Example code
from LanguageIdentifier import predict
from LanguageIdentifier import rank
print(predict("Det her er dansk"))
print(rank("This is english"))
predict outputs the most likely language of the sentence.
rank returns a list of tuples containing their respective probabilities.
da
[('ca', 2.175456259578823e-09), ('cs', 1.421048256844415e-08), ('da', 1.600260475242976e-06), ('de', 2.074262738460675e-06), ('en', 0.9998534917831421), ('es', 2.0248389631660757e-08), ('et', 9.649543386558435e-08), ('fi', 1.3886580063626752e-06), ('fr', 2.1743964850884367e-07), ('hr', 6.692872034363972e-08), ('hu', 0.00012513755063991994), ('it', 1.0744290079856e-07), ('lt', 9.55935547608533e-07), ('nl', 1.4533302419295069e-06), ('no', 6.45266709398129e-06), ('pl', 3.1909507924865466e-07), ('pt', 1.301345520232644e-07), ('ro', 6.668889795946598e-08), ('sv', 6.2374842855206225e-06), ('tr', 4.649361429187593e-08)]```
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
Built Distribution
Close
Hashes for LanguageIdentifier-1.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 788613b3dd3ef9533ad746ae34fe0ca8285316bc9b2a7093397da22c0d74481f |
|
MD5 | 6c7f0deadd6687306adb7a30240faf7e |
|
BLAKE2b-256 | 8483b1aac7ba062000a377407c75e9f6ac25bb4efd924f6a6b7ee5b2a9a82535 |