Bhashini AI Solutions Pvt Ltd

g2p

Grapheme-to-phoneme (G2P) conversion for Tamil / Kannada languages - a building block for Indic text-to-speech (TTS) systems

AudioRecorder

Audio Recording Android application

android-document-scanner

A A4-ish document scanner for Android, based on opencv

bhashini-ai.github.io

crnn.pytorch

Convolutional recurrent network in pytorch

DeepLearningExamples

Deep Learning Examples

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

IndicTrans2

Translation models for 22 scheduled languages of India

kotlin-toolkit

A toolkit for ebooks, audiobooks and comics written in Kotlin

NeMo-text-processing

NeMo text processing for ASR and TTS

radtts

Provides training, inference and voice conversion recipes for RADTTS and RADTTS++: Flow-based TTS models with Robust Alignment Learning, Diverse Synthesis, and Generative Modeling and Fine-Grained Control over of Low Dimensional (F0 and Energy) Speech Attributes.

readium-lcp-server

Repository for the Readium LCP Server

tts-survey

TTS_Utils

llama

Inference code for LLaMA models

sparrowhawk

sparrowhawk_nvidia

triton-clients

Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.