Detects the language of text
Project description
Text language identifier
This package serves as a wrapper for the most performant text language identifier.
Currently it wraps fasttext (NLLB version).
Before detecting the language, it preprocesses the text to improve results.
Usage
%pip install textlangid
import textlangid
lang = textlangid.detect("This is some text.")
top_languages = TextLanguageIdentifier.detect(text, top_k=3)
top_languages_with_confidence = TextLanguageIdentifier.detect(
text, top_k=3, return_confidence=True
)
top_languages_with_threshold = TextLanguageIdentifier.detect(
text, top_k=3, return_confidence=True, confidence_threshold=0.2
)
The language is returned in a FLORES-200 language code. Full list available here.
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
textlangid-0.0.7.tar.gz
(2.9 kB
view details)
Built Distribution
File details
Details for the file textlangid-0.0.7.tar.gz
.
File metadata
- Download URL: textlangid-0.0.7.tar.gz
- Upload date:
- Size: 2.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8ae0a84532bb5b1027fa4d2ca263d6e0cbcd00a94d39338a3d1a90672ac554cd |
|
MD5 | 8e47b3c7d1c424df543c426a3430f06f |
|
BLAKE2b-256 | 1d5abe0c24cc44f1218b5e41fce45c00c5b23c92d0942246516144e90c91a6e8 |
File details
Details for the file textlangid-0.0.7-py3-none-any.whl
.
File metadata
- Download URL: textlangid-0.0.7-py3-none-any.whl
- Upload date:
- Size: 3.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.9.20
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7ff35369cdbe95bbc7d8e46ad7df00de75a1bff6e2f363041701e9b96ef38dea |
|
MD5 | 40a2b7c1d0a8232d85f7057ebc70144b |
|
BLAKE2b-256 | 264ca39fc77d359481297d04d565dd4b8952a7bdee23d3c429538ffcf965bd28 |