Explore @skit-ai Open Source projects

Skit (@skit-ai)

skit-ai

Stars
655
Global Org. Rank 19,932 (Top 7 %)
Registered over 7 years ago
Most used languages

Python
49.0 %

Go
9.8 %

JavaScript
7.8 %

Jupyter Notebook
5.9 %

Shell
3.9 %

HTML
3.9 %

C++
2.0 %

Common Lisp
2.0 %

Emacs Lisp
2.0 %

C#
2.0 %

TeX
2.0 %

Elm
2.0 %

SCSS 2.0 %

Julia
2.0 %

Makefile 2.0 %

TypeScript
2.0 %
Location 🇮🇳 India
Country Total Rank 1,083
Country Ranking

Elm
6

Common Lisp
14

Julia
18

Emacs Lisp
25

TeX
32

SCSS 104

C++
198

Go
211

Makefile 348

Shell
392

Python
534

C#
752

Jupyter Notebook
938

JavaScript
2,859

HTML
3,460

kaldi-serve

Server framework for Kaldi ASR Toolkit

speech-to-intent-dataset

Dataset Release for Intent Classification from Speech

emotion-tts-dataset

Dataset release for Emotional TTS in Indian Accent

hiring

Hiring resources for roles at Skit

talks

Talks, presentations, workshops.

slu-prosody

Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 2023.

Jupyter Notebook

tog

A hackable Emacs based data-tagging framework

speech-recognition

SDKs and docs for Skit's speech to text service

woc-tts-enhancement

This is a winter of code project aimed at speech enhancement of text to speech models.

Jupyter Notebook

vcore

Common, utility packages for Go

mrcp-load-balancer

An MRCP server load balancer using OpenSIPS

dialogy

Language understanding toolkit for human dialogs.

paper-reading

Notes from our paper reading sessions

job-descriptions

Job descriptions for Tech roles at Skit

N-Best-ASR-Transformer

Code for ACL-IJCNLP 2021 paper "N-Best-ASR-Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses."

phone-number-entity-dataset

Dataset Release for Phone Number Entity capture task

dagre-py

Thin python wrapper around dagre-d3

Map-Mix

The official implementation of the method discussed in the paper Improving Spoken Language Identification with Map-Mix(work accepted at ICASSP-2023)

ml-katas

Katas for Machine Learning

elm-flow-chart

Create flowcharts in elm

tech

Skit's tech website

several-people-are-talking

Audio archive of reading club discussions at Vernacular.ai

styleguide

Programming style guide

plute

Framework for building SLU systems

ccb

Slack bot for virtual coffee pairing

eevee

Evaluation utilities

tts-middleware

Middleware module for our speech synthesis systems

Multimodal-Slu

This repo builds an top of self-supervised speech embeddings using S3PL tool-kit and Text based transformers from Huggingface to explore multi-modal SLU

ink-simulator

Ink based flow simulator

abcd

abcd is an allocation server for online experiments

sentinel

Skit's call monitoring and filtering framework.

ml

Machine Learning at Vernacular.ai

dialogy-template-simple-transformers

Dialogy template using simple transformers.

books-about-companies

Collection of books about the founding stories of different companies

errors

jaglar

Tool for project management backed by tj

engineering

Engineering at Vernacular.ai

stitch

Audio stitcher from pool of labelled recordings

skit-pipelines

Reusable workflows for ml using kubeflow components.

handbook

How Skit operates and other notes

trail

CLI to run your dataframes against SLU service and generated labeled dataframe.

sphinxcontrib-vai

Sphinx extensions

skit-labels

Command line interface for interacting with Label studio and (deprecated) tog data server

skit-auth

Authorization for skit.ai's platform.

android-sdk

Android SDK for chatbots built on vernacular.ai's platform

curriculum

Onboarding curriculum for Skit tech

lockdown-stats

Visualizations about Vernacular's work during lockdown

artifact-registry

Go SDK to manage artifacts stored by Kubeflow via MLMD.

pride

Simple pride rainbow top ribbon for your website

st-record

Streamlit component for recording audio

lute

Lute is a framework for writing compute DAGs

Improving-Numeric-ASR-via-Cues

Code and datasets for paper "Improving Alphanumeric Automatic Speech Recognition Via Cues"

slu-service

A microservice to expose the SLU API at skit.

multi_modal_emotion_classifier

This repo has code base to create multi modal emotion classifiers

vivaldi

Tools for working with VIVA data formats

openai-billing-analysis

Key wise cost reporting tool

onboarding

Artifacts from onboarding sessions

Jupyter Notebook

DiaML

Specification of DiaML and related utilities