SOTAVerified

Language Identification

Language identification is the task of determining the language of a text.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 794 papers

TitleStatusHype
CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-trainingCode11
An Initial Investigation of Language Adaptation for TTS Systems under Low-resource ScenariosCode2
MathPile: A Billion-Token-Scale Pretraining Corpus for MathCode2
TweetNLP: Cutting-Edge Natural Language Processing for Social MediaCode2
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority LanguagesCode1
Language-Informed Beam Search Decoding for Multilingual Machine TranslationCode1
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and BeyondCode1
MaskLID: Code-Switching Language Identification through Iterative MaskingCode1
FastSpell: the LangId Magic SpellCode1
Language and Speech Technology for Central Kurdish VarietiesCode1
KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text DetectionCode1
AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data FiltersCode1
GlotLID: Language Identification for Low-Resource LanguagesCode1
Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from WhisperCode1
Bhasha-Abhijnaanam: Native-script and romanized Language Identification for 22 Indic languagesCode1
An Open Dataset and Model for Language IdentificationCode1
Scaling Speech Technology to 1,000+ LanguagesCode1
PALI: A Language Identification Benchmark for Perso-Arabic ScriptsCode1
Improving Spoken Language Identification with Map-MixCode1
SOLD: Sinhala Offensive Language DatasetCode1
AfroLID: A Neural Language Identification Tool for African LanguagesCode1
The first neural machine translation system for the Erzya languageCode1
IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languagesCode1
Word-level Language Identification Using Subword Embeddings for Code-mixed Bangla-English Social Media DataCode1
L3Cube-HingCorpus and HingBERT: A Code Mixed Hindi-English Dataset and BERT Language ModelsCode1
Show:102550
← PrevPage 1 of 32Next →
All datasetsVOXLINGUA107GlotLID-CNordic Language IdentificationOpenSubtitlesUniversal DependenciesVoxForge

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1wav2vec 2.0 LV-60KError rate7.2—Unverified
2XLS-RError rate5.7—Unverified
#ModelMetricClaimedVerifiedStatus
1GlotLIDMacro F10.98—Unverified
#ModelMetricClaimedVerifiedStatus
1FastTextAccuracy0.97—Unverified
#ModelMetricClaimedVerifiedStatus
1Apple bi-LSTMAccuracy91.37—Unverified
#ModelMetricClaimedVerifiedStatus
1Apple bi-LSTMAccuracy86.93—Unverified
#ModelMetricClaimedVerifiedStatus
1ConformerG-PAccuracy99.8—Unverified