AI4Bhārat's repositories
IndicWav2Vec
Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2
NPTEL2020-Indian-English-Speech-Dataset
NPTEL2020: Speech2Text dataset for Indian-English Accent
IndicNLP-Transliteration
Codebase for Indic-Transliteration using Seq2Seq RNN. For latest repo with Transformer-based models, check: https://github.com/AI4Bharat/IndicXlit
indic-bart
Pre-trained, multilingual sequence-to-sequence models for Indian languages
Indic-Input-Tool-UI
Web Interface for Transliteration for Indic languages.
Fonts-for-Indian-Scripts
Font style transfer for Devanāgarī script using GANs
speech-transcript-cleaning
Perform cleaning and normalization to standardize speech transcripts (train and test) across datasets.
ezAnnotate
Annotation Platform for Machine Learning / Data Science, forked from DataTurks
indic-transliterate-js
Transliteration component for React with support for Indic langauges. Burhanuddin → बुरहानुद्दीन
workshop-nlg-nlu-2022
Material for AI Workshop on Natural Language Understanding and Generation
Chitralekha-Frontend-Lite
Lightweight version of Chitralekha
indicnlp.ai4bharat.org
Archived old website for AI4Bhārat Indic-NLP
quill-auto-complete
💬 Auto-complete for the Quill rich text editor
INCLUDE-MS-Teams-Integration
An experimental Microsoft Teams integration of Sign Language models for word-level sign recognition
sign-language.ai4bharat.org
Website for Indian Sign Language Recognition
Indic-Glossaries
Collection of datasets for glossaries in Indian languages
label-studio-frontend
Data labeling react app that is backend agnostic and can be embedded into your applications — distributed as an NPM package
Shoonya-Frontend-Old
Old version of Shoonya UI. Latest repo: https://github.com/AI4Bharat/Shoonya-Frontend
IndicSUPERB
Indic SUPERB
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Recorderjs
Repo for the recorder.js file
v0.ai4bharat.org
AI4Bhārat's Old Static Website Pages