Production First and Production Ready End-to-End Speech Recognition Toolkit

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

A playbook for systematically maximizing the performance of deep learning models.

A PyTorch-based Speech Toolkit

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Google Research

Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a ca…

Open deep learning compiler stack for cpu, gpu and specialized accelerators

NAT 内网穿透 远程内网计算机 域名访问内网站点 反向代理内网服务 花生壳 端口转发 http代理 微信 小程序 expose a local server behind a NAT or firewall to the internet like ngrok and frp. NAT ssh proxy tunnel reverse-proxy

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

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为TensorFlow 2.0实现，项目已得到李沐老师的同意

中文医疗NLP领域 数据集，论文 ，知识图谱，语料，工具包

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

Deep Xi: A Deep Learning Approach to A Priori SNR Estimation. Used for Speech Enhancement and robust ASR.

A PaddlePaddle implementation of DeepSpeech2 architecture for ASR.

A Spatial Audio Framework written in C [Ambisonics, VBAP, Spherical Array Processing, Sound-field Visualisation etc.]

🔊 A comprehensive list of open-source datasets for voice and sound computing (40+ datasets).

RTP Library

[CVPR2020] Surpassing MobileNetV3: "GhostNet: More Features from Cheap Operations"

A TensorFlow implementation of Baidu's DeepSpeech architecture

Header-only C++ library for low precision floating point type emulation.

CMSIS Version 5 Development Repository

Limiter, compressor, reverberation, equalizer and auto volume effects for Pulseaudio applications

A curated list of amazingly awesome open source resources related to broadcast technologies

A technical report on convolution arithmetic in the context of deep learning

Synchronous multi-room audio player

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，近30万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系[email protected] 版权所有，违权必究 Tan 2018.06

header only, dependency-free deep learning framework in C++14

📡 All You Need to Know About Deep Learning - A kick-starter