ZhangAustin

cocktailparty

Multi-Modal Multi-Channel System and Corpus For Cocktail Party Problem

algo

Set up a personal VPN in the cloud

ASRT_SpeechRecognition

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

asteroid

The PyTorch-based audio source separation toolkit for researchers || Pretrained models available

AugLy

A data augmentations library for audio, image, text, and video.

BigCiDian

Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.

chinese_text_normalization

Chinese text normalization for speech processing

edex-ui

A cross-platform, customizable science fiction terminal emulator with advanced monitoring & touchscreen support.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

GiantMIDI-Piano

google-research

Google Research

Halide

a language for fast, portable data-parallel computation

Hey-Jetson

Deep Learning based Automatic Speech Recognition with attention for the Nvidia Jetson.

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

lhotse

local-llms-analyse-finance

In this project, I explored how local LLMs can be used to label data and support analyses. Specifically, I used Llama2 model to automatically categorise my bank transaction data.

Megatron-LLM

distributed trainer for LLMs

MMdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

netron

Visualizer for deep learning and machine learning models

Nuklear

A single-header ANSI C immediate mode cross-platform GUI library

odas

ODAS: Open embeddeD Audition System

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, speaker embedding

pyctcdecode

A fast and lightweight python-based CTC beam search decoder for speech recognition.

pyflow

Fast, accurate and easy to run dense optical flow with python wrapper

PythonRobotics

Python sample codes for robotics algorithms.

pytorch-struct

Fast, general, and tested differentiable structured prediction in PyTorch

rendezvous

Next generation videoconference system

rnnt_decoder_cuda

An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.

SincNet

SincNet is a neural architecture for efficiently processing raw audio samples.

vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node