MultiLexNorm 2021 competition system from ÚFAL
-
Updated
Dec 30, 2021 - Python
#
byt5
Here are 11 public repositories matching this topic...
Automated pipeline for expanding medieval Latin abbreviations encoded in TEI using finetuned ByT5. Drop your TEI files, run five scripts, and get a Hugging Face dataset plus a lightweight LoRA adapter for ByT5 that turns graphemic ATR output into expanded text.
-
Updated
Jul 31, 2025 - Python
This repository contains a number of experiments with Multi Lingual Transformer models (Multi-Lingual BERT, DistilBERT, XLM-RoBERTa, mT5 and ByT5) focussed on the Dutch language.
nlp text-classification transformers bert mt5 linearsvc tensorflow2 distilbert xlm-roberta transformers-models multilingual-bert byt5
-
Updated
Oct 30, 2023 - Python
Official code for "Fine-Tashkeel at KSAA-2026" — Systematic evaluation of 18 Seq2Seq, token classification, decoder LLM, and ASR models for automatic Arabic text diacritization. 5th place at KSAA-2026 Shared Task (OSACT7 @ LREC 2026).
transformers seq2seq speech-to-text arabic arabic-nlp diacritization shared-task tashkeel byt5 lrec2026
-
Updated
Mar 23, 2026 - Jupyter Notebook
A high-performance unified Sanskrit NLP parser for Padaccheda (word segmentation), morphological analysis, lexicon lookup, Akshara breakdown, Google translate Integration, multi-script transliteration, and an embeddable web reader plugin.
linguistics nlp-parsing devanagari sanskrit-grammar streamlit google-translate-free-api byt5 aksharamukha hellwig-method akshara dharmamitra samvadah
-
Updated
Aug 18, 2026 - Python
UrduNexus is an AI-powered Roman Urdu to Native Urdu transliteration engine built with a fine-tuned ByT5 model, FastAPI, and Edge-TTS voice integration.
-
Updated
Jun 8, 2026 - Jupyter Notebook
Computational analysis of Sanskrit morphology and English narrative networks in the Mahābhārata using ByT5-Sanskrit NLP
nlp sentiment-analysis transformers computational-linguistics digital-humanities network-analysis sanskrit mahabharata byt5
-
Updated
Jan 16, 2026 - Jupyter Notebook
Explainable hybrid Uzbek morpheme analyzer powered by ByT5, linguistic rules, human feedback and Uzbek TTS.
-
Updated
Jul 25, 2026 - Python
Translating 4,000-year-old Old Assyrian cuneiform into English with byte-level ByT5 models — a Kaggle competition project (final private score 32.46).
nlp machine-translation transformers kaggle cuneiform low-resource-languages akkadian huggingface byt5
-
Updated
Jun 27, 2026 - Python
Evaluate Arabic speech dictation diacritization models with KSAA 2026 results, code, and benchmarks for seq2seq and multimodal approaches
transformers seq2seq speech-to-text arabic arabic-nlp diacritization shared-task tashkeel byt5 lrec2026
-
Updated
Aug 24, 2026 - Jupyter Notebook
Improve this page
Add a description, image, and links to the byt5 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the byt5 topic, visit your repo's landing page and select "manage topics."