Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

Recovering Whisper's Wasted Output Capacity for Ge'ez-Script Languages: A Controlled Tokenizer-Extension Study on Amharic

Domaine:

natural language processing

Type de record:

paper
Créateur:
FeyTheMah
Éditeur:
unp
Hôte:avatar

Visit

doi.orgwww.researchgate.net

Languages

Amharic

Similaires

Ethiopic scroll in Amharic script, Ge'ez. IE TCD MS 11082A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez ScriptExpanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and TigrinyaDeep learning for Ethiopian Ge'ez script optical character recognisionGe'ez / Amharic handwritten digitsmisge10/amharic-tokenizer

Ethiopic scroll in Amharic script, Ge'ez. IE TCD MS 11082

Digitised version of IE TCD MS 11082, an Ethiopic scroll in Amharic script, possibly Ge'ez. No corre

A Case Against Implicit Standards: Homophone Normalization in Machine Translation for Languages that use the Ge'ez Script

Homophone normalization, where characters that have the same sound in a writing script are mapped to

Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya

Multilingual pre-trained language models (PLMs) exhibit degraded performance on low-resource, non-La

Deep learning for Ethiopian Ge'ez script optical character recognision

Ge'ez / Amharic handwritten digits

misge10/amharic-tokenizer