iLID

Language identifier

A deep learning-based system for identifying spoken language in audio files.

automatic spoken language identification

GitHub

90 stars
13 watching
24 forks
Language: Python
last commit: about 6 years ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
ajaech/twitter_langid An open-source software framework for training and evaluating hierarchical neural networks for language identification tasks. 15
alvations/sugarlike A tool that identifies languages in text by comparing them to a reference set of patterns. 1
cisnlp/glotlid A language identification model that supports over 2000 languages and can be used for various NLP tasks. 90
pemistahl/lingua An accurate language detection library for Java and the JVM suitable for both short and long text inputs. 707
vseloved/wiki-lang-detect Uses Wikipedia data to identify the language of unstructured text 31
alvations/sugali A system designed to identify the language of an arbitrary text string using machine learning and multiple data sources. 2
greyblake/whatlang-rs A Rust library for detecting the language of text, including script recognition and reliability estimation. 970
pemistahl/lingua-go A library that accurately detects the language of short to long text inputs without requiring external APIs or configuration. 1,190
pld-linux/apertium-dict-es-gl A dictionary file for machine translation between two languages using a specific rule-based machine translation system 1
umpirsky/language-list A comprehensive repository of language information in various formats 517
olivomarco/lc4j An open-source Java library implementing text categorization and language detection using N-grams. 5
teknologi-umum/flourite Automatically detects programming languages from given strings. 38
jxxcarlson/l1 A language demo project showcasing fault-tolerant parsing techniques for a simple language with a Lisp-like syntax. 0
system-t/dimsim A phonetic similarity algorithm for indexing Chinese characters by sound 120
unlyed/universal-language-detector Detects and resolves the language used in user requests 95