Starred repositories
A pure python module for reading and writing kaldi ark files
Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.
This is a mirror of Distant Speech Recognition project using svn2git
This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )
A guideline for building practical production-level deep learning systems to be deployed in real world applications.
Juicer is a Weighted Finite State Transducer (WFST) based decoder for Automatic Speech Recognition (ASR).
Google Research
dabnn is an accelerated binary neural networks inference framework for mobile platform
OpenSource G711, G722, G729, Opus & Other Format VoIP SIP Recorder
Reference models and tools for Cloud TPUs.
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding a…
A curated list of awesome SLAM tutorials, projects and communities.
😎 A curated list of robotics libraries and software
SLAM study following GAO Xiang's 14 Lectures about Visual SLAM.
mixup: Beyond Empirical Risk Minimization
A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility
Putting TensorFlow back in PyTorch, back in TensorFlow (differentiable TensorFlow PyTorch adapters).
NumPy aware dynamic Python compiler using LLVM
A mix of GAN implementations including progressive growing
An implementation of a deep learning recommendation model (DLRM)
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.