Pinned Repositories
ajkaanbal.github.io
ajkaanbal pages
alpine-git
dhall-argo
dockerfiles
Just some dockerfiles
dotfiles
payu
Python API for PayU Latam
pipelines
Machine Learning Pipelines for Kubeflow
queryinspector
scrom-frontend
ajkaanbal's Repositories
ajkaanbal/dotfiles
ajkaanbal/dhall-argo
ajkaanbal/dockerfiles
Just some dockerfiles
ajkaanbal/alpine-git
ajkaanbal/argo-dataflow
ajkaanbal/argo-workflows
Argo Workflows: Get stuff done with Kubernetes.
ajkaanbal/pipelines
Machine Learning Pipelines for Kubeflow
ajkaanbal/queryinspector
ajkaanbal/coc-metals
coc.nvim extension for Metals, the Scala language server
ajkaanbal/cortex
A horizontally scalable, highly available, multi-tenant, long term Prometheus.
ajkaanbal/cv
Resume
ajkaanbal/druid
阿里巴巴数据库事业部出品，为监控而生的数据库连接池
ajkaanbal/flux-workshop-2023
Flux Workshop 2023-08-10
ajkaanbal/graphql-client
ajkaanbal/hue
Hue is an open source SQL Cloud Assistant for developing and accessing SQL/Data Apps.
ajkaanbal/jira-cli
ajkaanbal/jq-docker
ajkaanbal/kubie
A more powerful alternative to kubectx and kubens
ajkaanbal/lightline.vim
A light and configurable statusline/tabline plugin for Vim
ajkaanbal/natchez-extras
Integrations between Natchez, Doobie, HTTP4s, Log4cats and Datadog. Formerly called effect-utils.
ajkaanbal/nvim-metals
A Metals plugin for Nvim
ajkaanbal/opentracing-scala
ajkaanbal/OSSRH-62293
ajkaanbal/pandas-alpine
ajkaanbal/pruebita
ajkaanbal/pulseaudio-config
Scripts and notes for custom pulseaudio configuration
ajkaanbal/slack-bot
ajkaanbal/spark-on-k8s-operator
Kubernetes operator for managing the lifecycle of Apache Spark applications on Kubernetes.
ajkaanbal/ssh-client-alpine
ajkaanbal/svoice
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.