Ashish Alex's Projects
Unofficial Pytorch Implementation Of AdversarialAutoAugment(ICLR2020)
šØ Format code in your clipboard with Prettier
The PyTorch-based audio source separation toolkit for researchers
A website that displays audio and its spectrogram when an augmentation/operation is applied to the audio.
Customisable web based bigquery local IDE
Nodejs extension host for vim & neovim, load extensions like VSCode and host language servers.
Dataform is a framework for managing SQL based data operations in BigQuery
Audio Source Separation Without Any Training Data.
Dataform json parser
Docker Image for the Madness Markdown Server
A markdown version emoji cheat sheet
Display opencv video on your flask app.
Shows the graph between two football players indicating the shortest connection between them.
cli to format .sqlx files in Dataform project
Helper commands to get started with using machine learning libraries on Nvidia Jetson Nano
Markdown Cheatsheet for Github Readme.md
Interactive database client for neovim
A parallel programming implementation in C using OpenMP
Neovim configuration using lazy
Extreme Learning Machine implementation in Python
Uses tokenized query returned by python-sqlparse and generates query metadata
We provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
My development environment and system setup guides
Find, Filter, Preview, Pick. All lua, all the time.
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)