Popular GitHub Repositories for Dialect Preservation

A suite of Arabic natural language processing tools developed by the CAMeL Lab at New York University Abu Dhabi.

SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (ECCV2020)

TTS for pitch-accented language. Korean dialect DB.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset. TunBERT was applied to three NLP downstream tasks: Sentiment Analysis (SA), Tunisian Dialect Identification (TDI) and Reading Comprehension Question-Answering (RCQA)

Qwen-TTS offers a robust voice synthesis service using FastAPI, supporting bilingual and dialect options. Explore seamless audio generation on GitHub! ??

(NeurIPS 2022) Official Implementation of "Preservation of the Global Knowledge by Not-True Distillation in Federated Learning"

DuckDB Community Extension implementing ClickHouse SQL Dialect macros and Custom functions for DuckDB

LLM-based Dialect Translation System

End to End Dialect Identification using Convolutional Neural Network

This is a repository of the Multi-dialect Arabic BERT model.

Tunisian Sentiment Analysis Corpus.

carML - a yummy and sweet ML dialect

Code for paper "Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation" EMNLP 2021 and "Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation" arXiv 2020

Source code for "Improving Attention Mechanism in Graph Neural Networks via Cardinality Preservation" (IJCAI 2020)

Fine-tune BERT models to classify Arabic text by different dialects.

The official submission from Speech Squad team for the MTC-AIC 2 competition of 2024 where an ASR model is developed tailored for the Egyptian dialect, utilizing the FastConformer architecture. Our four-stage training pipeline achieved a Mean Levenshtein Distance score of 9.58 on the test set.

ArSarcasm-v2 is an extension to the original ArSarcasm dataset. It was used for the shared task on sarcasm detection and sentiment analysis, which is a part of WANLP 2021.

A Banking chatbot solution built with RASA using four languages: Arabic, English, French and Tunisian dialect This solution aims to provide users with response to commonly asked questions about bank services as well as taking actions such as: User sign-up User sign-in (Flask interface) Currency convertor Money Transfer Email notifications Id card verification through camera using AI The chat bot was deployed on Messanger and on a Flask web site

The aim of the Bachelor project is to innovate a new way for Arabic (Egyptian-Dialect) Sentiment Analysis , Forecasting and Topic Modeling using Machine Learning , Deep Learning and Transformers!

Инструмент улучшения качества аниме-видео с сохранением звука, работает на Windows, Linux и macOS, использует Real-ESRGAN и пакетную обработку.