End-to-End Speech Processing Toolkit

NOTSOFAR-1 Challenge: Distant Diarization and ASR

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

The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

A collaborative catalog of NLP resources for Indic languages

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

Cool Python features for machine learning that I used to be too afraid to use. Will be updated as I have more time / learn more.

Largest list of Arabic stop words on Github. أكبر قائمة لمستبعدات الفهرسة العربية على جيت هاب

LLM training in simple, raw C/CUDA

Kolmogorov Arnold Networks

Unofficial implementation of NVIDIA P-Flow TTS paper

Schedule-Free Optimization in PyTorch

A collection of learning resources for curious software engineers

The official PyTorch implementation of Google's Gemma models

NeMo: a toolkit for conversational AI

A benchmark corpus for ASR hypothesis revising task

Translation models for 22 scheduled languages of India

Marathi NLP - is a repository dedicated to development of tools and resources for Marathi language.

Python code for training and testing of GMM-UBM and maximum a posterirori (MAP) adaptation based speaker verification

A drop-in collection of CSS styles to make simple websites just a little nicer

Main application code for Ambuda, a breakthrough Sanskrit library (ambuda.org)

A YouTube scraper for scraping channels, playlists, and searching 🔎

A feature-rich command-line audio/video downloader

Speech-to-text server framework with next-gen Kaldi

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

macOS system monitor in your menu bar