AnkushMalaker

speech-emotion-recognition

Implementation of the paper "Speech emotion recognition with deep convolutional neural networks" by Dias Issa Et al.

pretrained-dcnn-attention-ser

Tensorflow Implementation for "Pre-trained Deep Convolution Neural Network Model With Attention for Speech Emotion Recognition"

aits

AI Text Search

AnkushMalaker

asr-webservice

ASR Webservice API

Knowledgebase

Knowledgebase repository started in month of March 2021

core

:house_with_garden: Open source home automation that puts local control and privacy first.

crispy

Crispy is a machine-learning algorithm to make video-games montages efficiently. It uses a neural network to detect highlights in the video-game frames

easy-stt

Easy way to use one of transformer models to do inference locally. Can be done live through mic, or on local files. The first run needs to be online to download necessary models.

excalidraw-recognition

Virtual whiteboard for sketching hand-drawn like diagrams

homeassistant-satellite

Streaming audio satellite for Home Assistant

icassp2021-mscnn-spu

Code for our paper "Efficient Speech Emotion Recognition Using Multi-Scale CNN and Attention" (ICASSP 2021, co-first authorship)

laughr

Recurrent neural network audio manipulation tool to mute "laugh track" audio segments found commonly in sitcoms.

LiveEd-Smart-Teachers-App

LiveEd is a smart application meant for virtual teachers allowing them to teach from anywhere in the world. It allows teachers to draw in the air as they would using a whiteboard and also import images into the screen to show them to the viewers.

nanoGPT-agent

The simplest, fastest repository for training/finetuning medium-sized GPTs.

obsidian-aicommander-plugin-local

openWakeWord

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

pi-camera-stream-flask

[Docker] Create your own live camera stream using a Raspberry Pi 4

piper-recording-studio

Local voice recording for creating Piper datasets

python-audio-interfaces

Easy audio interfaces in python

pytorch-attention

Attention mechanisms implemented with basic math and pytorch to gain an understanding. This is kept intentionally feature-poor so as to not be confusing.

RustProjects

Rust Projects I made while learning from "The Book"

TC-ResNet-PyTorch

translate-with-whisper-live

dibs on implementing a live stream version

whisper-autotune

whisper-obsidian-plugin-local

Speech-to-text in Obsidian using Local Whisper

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

wyoming-addons

Docker builds for Home Assistant add-ons using Wyoming protocol

wyoming-distil-whisper

Wyoming protocol server for distil-whisper speech to text system

yolo_v1_pytorch

PyTorch implementation of YOLO-v1 including training