Discover AI4Bharat/indic-asr-api-backend Open Source project

Translation models for 22 scheduled languages of India

273

IndicTrans2

Description Describes the IndicNLP corpus and associated datasets

223

indicnlp_corpus

Text-to-Speech for languages of India

149

Indic-TTS

indicTranslate v1 - Machine Translation for 11 Indic languages. For latest v2, check: https://github.com/AI4Bharat/IndicTrans2

130

indicTrans

👐OpenHands : Making Sign Language Recognition Accessible. | **NOTE:** No longer actively maintained. If you are interested to own this and take it forward, please raise an issue

111

OpenHands

Chitralekha - A video transcreation platform for Indic languages, supporting transcription, translation and voice-over

Chitralekha

IndicLLMSuite

A blueprint for creating Pretraining and Fine-Tuning datasets for Indic languages

Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2

IndicWav2Vec

Transliteration models for 21 Indic languages

IndicXlit

NPTEL2020: Speech2Text dataset for Indian-English Accent

NPTEL2020-Indian-English-Speech-Dataset

Pretraining, fine-tuning and evaluation scripts for IndicBERT-v2 and IndicXTREME

IndicBERT

Codebase for Indic-Transliteration using Seq2Seq RNN. For latest repo with Transformer-based models, check: https://github.com/AI4Bharat/IndicXlit

IndicNLP-Transliteration

Shoonya - Platform to Annotate and label data at scale.

Shoonya

vistaar

Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR

Pre-trained, multilingual sequence-to-sequence models for Indian languages

indic-bart

Transcribe your videos and translate it into Indic languages.

Chitralekha-Backend

Web Interface for Transliteration for Indic languages.

Indic-Input-Tool-UI

DRF-based API server for Shoonya platform

Shoonya-Backend

Swarah: Indian-English speech dataset collected across the country

Svarah

A Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS

IndicVoices-R

FBI

FBI: Finding Blindspots in LLM Evaluations with Interpretable Checklists

Shoonya-Frontend

Dhruva is an open-source platform for serving language AI models at scale.

Dhruva-Platform

TypeScript

INCLUDE

Code for INCLUDE paper with pre-trained models

Synthetically generate random text document images with ground-truth

DocSim

Font style transfer for Devanāgarī script using GANs

Fonts-for-Indian-Scripts

Additional resources from our AACL tutorial

aacl23-mnmt-tutorial

adapter-efficiency

Language Identification for Indian languages

IndicLID

Setu is a comprehensive pipeline designed to clean, filter, and deduplicate diverse data sources including Web, PDF, and Speech data. Built on Apache Spark, Setu encompasses four key stages: document preparation, document cleaning and analysis, flagging and filtering, and deduplication.

setu

HTML

speech-transcript-cleaning

Perform cleaning and normalization to standardize speech transcripts (train and test) across datasets.

Annotation Platform for Machine Learning / Data Science, forked from DataTurks

ezAnnotate

Anudesh-Frontend

Frontend for Chitralekha platform

Chitralekha-Frontend

The code for transactional voice AI

transactional-voice-ai

Glossary service for Indian languages

Indic-Glossary-Explorer

Material for AI Workshop on Natural Language Understanding and Generation

workshop-nlg-nlu-2022

indicnlp.ai4bharat.org

Archived old website for AI4Bhārat Indic-NLP

HTML

Chitralekha-Frontend-Lite

Lightweight version of Chitralekha

Collection of datasets for glossaries in Indian languages

Indic-Glossaries

CIA

Code for training, evaluating and using a cross-lingual Auto Evaluator

Website for Indian Sign Language Recognition

sign-language.ai4bharat.org

INCLUDE-MS-Teams-Integration

An experimental Microsoft Teams integration of Sign Language models for word-level sign recognition

Anudesh-Backend

IndicMT Eval: A Dataset to Meta-Evaluate Machine Translation Metrics for Indian Languages, ACL 2023

IndicMT-Eval

HTML

IndicVoices

A simple lightweight library for text normalization for Indian Languages

indic-numtowords

IndicSUPERB

Deployment code for all the Transactional Voice AI modules.

transactional-voice-ai_serving

C++

CTQScorer

IndicSwipe is a collection of datasets and neural model architectures for decoding swipe gesture inputs on touch-based Indic language keyboards across 7 languages.

Indic-Swipe

Codebase for NLTM DMU's Data Upload System

Indic-OCR

DMU-DataDaan

Old website of AI4Bhārat using TinaCMS

2022.ai4bharat.org

setu-translate

A one stop platform to try out all the models built by the AI4Bharat team.

models.ai4bharat.org

Old version of Shoonya UI. Latest repo: https://github.com/AI4Bharat/Shoonya-Frontend

Shoonya-Frontend-Old

Transliteration Web Interface

Varnam-Transliteration-UI

A tool to perform functional testing and performance testing of the Dhruva Platform

ai4b-website

TypeScript

Dhruva-Evaluation-Suite

Natural Language Understanding resources for Indian languages

indicnlp_suite

Input-Tools-By-AI4bharat

Enhance your typing experience in Chrome with AI4Bharat's Input Tools Chrome extension. This extension provides real-time transliteration suggestions for Indian languages, offering seamless integration into your typing workflow.

This repository holds the artifacts of 'LAHAJA: A Robust Multi-accent Benchmark for Evaluating Hindi ASR Systems'

Lahaja

Rasa

Expressive TTS Dataset for Assamese, Bengali, and Tamil.

NeMo

VocabAdaptation_LLM