AI4Bharat / IndicTrans2Links
Translation models for 22 scheduled languages of India
☆343Updated 3 months ago
Alternatives and similar repositories for IndicTrans2
Users that are interested in IndicTrans2 are comparing it to the libraries listed below
Sorting:
- Pretraining, fine-tuning and evaluation scripts for IndicBERT-v2 and IndicXTREME☆100Updated 4 months ago
- A blueprint for creating Pretraining and Fine-Tuning datasets for Indic languages☆107Updated 10 months ago
- Transliteration models for 21 Indic languages☆95Updated last year
- indicTranslate v1 - Machine Translation for 11 Indic languages. For latest v2, check: https://github.com/AI4Bharat/IndicTrans2☆129Updated last year
- Chitralekha - A video transcreation platform for Indic languages, supporting transcription, translation and voice-over☆106Updated 7 months ago
- A New Tamil Large Language Model (LLM) Based on Llama 2☆311Updated last year
- Open source speech to text models for Indic Languages☆306Updated 2 years ago
- A collaborative catalog of NLP resources for Indic languages☆606Updated 7 months ago
- A simple, consistent and extendable toolkit for IndicTrans2. (Pypi: https://pypi.org/project/indictranstoolkit)☆34Updated 2 weeks ago
- Text-to-Speech for languages of India☆260Updated 8 months ago
- ☆31Updated last year
- A Continually LoRA PreTrained and FineTuned 7B Llama-2 Indic model for Malayalam Language.☆61Updated last year
- Repository for fine-tuning gemma models using unsloth for indic languages☆95Updated last year
- Code repository for "Introducing Airavata: Hindi Instruction-tuned LLM"☆60Updated 9 months ago
- Description Describes the IndicNLP corpus and associated datasets☆177Updated 2 years ago
- Awesome List of Tamil NLP & AI Resources☆113Updated 2 years ago
- Marathi NLP - is a repository dedicated to development of tools and resources for Marathi language.☆142Updated last month
- Python package for indic script transliteration☆191Updated 3 weeks ago
- ☆29Updated last year
- Shoonya - Platform to Annotate and label data at scale.☆56Updated 11 months ago
- IndicGenBench is a high-quality, multilingual, multi-way parallel benchmark for evaluating Large Language Models (LLMs) on 4 user-facing …☆51Updated 11 months ago
- A pipeline for transliteration, spell correction, POS tagging and word sense disambiguation of Hinglish code mixed data to Hindi Devanaga…☆36Updated last year
- Language Identification for Indian languages☆22Updated last year
- A Catalog lists instruction sets, models available for Indic language☆9Updated last year
- A lightweight evaluation suite tailored specifically for assessing Indic LLMs across a diverse range of tasks☆37Updated last year
- Resources and tools for Indian language Natural Language Processing