anteju Goto Github PK

aistore

AIStore: scalable storage for AI applications

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

audio

Data manipulation and transformation for audio signal processing, powered by PyTorch

dns-challenge

This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.

encodec

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

espnet

End-to-End Speech Processing Toolkit

gss

A simple package for Guided source separation (GSS)

lhotse

Tools for handling speech data in machine learning projects.

lightning

The most intuitive, flexible, way for researchers, ML engineers and data scientists to build models (with PyTorch), research workflows and production pipelines with an obsessive focus on flexibility and performance.

mir_eval

Evaluation functions for music/audio information retrieval/signal processing algorithms.

narrowband_deepfiltering

nemo

NeMo: a toolkit for conversational AI

pyroomacoustics

Pyroomacoustics is a package for audio signal processing for indoor applications. It was developed as a fast prototyping platform for beamforming algorithms in indoor scenarios.

speechbrain

A PyTorch-based Speech Toolkit

srmrpy

Python implementation of the SRMR toolbox

torchdata

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

transformerengine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.