ahmedheakl / arazn-llmLinks
Code-Switched translations with Large Language models
☆24Updated 11 months ago
Alternatives and similar repositories for arazn-llm
Users that are interested in arazn-llm are comparing it to the libraries listed below
Sorting:
- The official implementation of CATT Arabic diacritization models.☆54Updated 4 months ago
- ☆59Updated 4 months ago
- Several deep learning models for restoring Arabic diacritics using Pytorch.☆35Updated 3 years ago
- Code, models, and data for "Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation". EMNLP 2023.☆17Updated last year
- ☆42Updated 2 years ago
- A framework for Arabic spelling correction using different seq2seq model architectures such as transformers and RNNs☆23Updated last year
- ☆128Updated last year
- Code for Arabic Nougat☆48Updated 11 months ago
- This is a diacritization model for Arabic language. This model was built/trained using the Tashkeela: the Arabic diacritization corpus on…☆45Updated 2 years ago
- Python intefrace for evaluation on chatgpt models☆19Updated last year
- Instruction dataset for Arabic with 10,000 instruction and output pairs. CIDAR can be used to fine-tune LLMs to follow instructions.☆43Updated 7 months ago
- The largest public catalogue for Arabic NLP and speech datasets. There are +500 datasets annotated with more than 25 attributes.☆186Updated this week
- Official Repository of the Deep Diacritization Paper☆16Updated 4 years ago
- TTS for Arabic (FastPitch, Mixer-TTS) in the ONNX format☆31Updated 2 months ago
- Aranizer: A Custom Tokenizer based on SentencePiece and BPE tailored for Arabic Language Modeling☆21Updated last year
- TTS models for Arabic (Tacotron2, FastPitch)☆128Updated last year
- Neural Arabic text diacritization☆93Updated 2 years ago
- Add Arabic diacritics (tashkeel/harakat) using Rust/Python/C++/WASM and NLP models☆36Updated last month
- أسئلة باللغة العربية تركز على الثقافة السعودية تم اختبارها على عدد من النماذج اللغوية الضخمة LLMs☆17Updated 9 months ago
- This is the official repository for Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks.☆26Updated 11 months ago
- TURJUMAN, a neural toolkit for translating from 20 languages into Modern Standard Arabic (MSA).☆57Updated 2 years ago
- Arabic cleaning, normalization and segmentation library.☆72Updated 2 years ago
- Benchmark Arabic text diacritization dataset☆76Updated 6 years ago
- Arabic deep-learning based diacritization models (Shakkala, Shakkelha) ported to PyTorch☆14Updated 2 years ago
- This repository contains code for fine-tuning the Whisper speech-to-text model.☆18Updated 3 weeks ago
- Convert Arabic diacritised text to a sequence of phonemes and create a pronunciation dictionary from them for alignment using HTK☆63Updated 8 years ago
- Arabic speech recognition, classification and text-to-speech.☆413Updated 2 years ago
- [ACL 2025 🔥] A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding☆59Updated 5 months ago
- A simple library to correct the misspelling for Arabic language.☆14Updated 4 years ago
- Context-Sensitive Neural Spelling Checker☆20Updated last year