Pinned Repositories
ATC-Anno
ATC-Anno is an annotation tool for Air Traffic Control data that offers automatic semantic and concept annotation.
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
boriskra
Config files for my GitHub profile.
DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
EdgeML
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
embox
Modular and configurable OS for embedded applications
ipfs
Peer-to-peer hypermedia protocol
Multi-Source-Sound-Localization
This repo aims to perform sound localization in complex audiovisual scenes, where there multiple objects making sounds.
neuroflight
Next Generation Flight Controller Firmware
odas
ODAS: Open embeddeD Audition System
boriskra's Repositories
boriskra/neuroflight
Next Generation Flight Controller Firmware
boriskra/ATC-Anno
ATC-Anno is an annotation tool for Air Traffic Control data that offers automatic semantic and concept annotation.
boriskra/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
boriskra/boriskra
Config files for my GitHub profile.
boriskra/DNS-Challenge
This repo contains the scripts, models, and required files for the Deep Noise Suppression (DNS) Challenge.
boriskra/EdgeML
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
boriskra/embox
Modular and configurable OS for embedded applications
boriskra/ipfs
Peer-to-peer hypermedia protocol
boriskra/Multi-Source-Sound-Localization
This repo aims to perform sound localization in complex audiovisual scenes, where there multiple objects making sounds.
boriskra/odas
ODAS: Open embeddeD Audition System
boriskra/odas_ros
ODAS ROS package
boriskra/odas_web
A desktop visualization GUI for the ODAS library
boriskra/ptpd
PTPd official source - master branch a.k.a. trunk
boriskra/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
boriskra/SparkFun_ICM-20948_ArduinoLibrary
Arduino support for ICM_20948 w/ portable C backbone
boriskra/stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
boriskra/Synaction
A PTP (IEEE1588-2008) Implementation for iOS with statistical methods to deal with jitter.
boriskra/tinyengine
[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory