An IVR Chatbot which can exponentially reduce the burden of companies as well as can improve the consumer/end user experience.

Overview

IVR-Chatbot

Achievements ๐Ÿ†

Team Uhtred won the Maverick 2.0 Bot-a-thon 2021 organized by AbInbev India.

โ“ Problem Statement

As we all know that, lot of tedious/complex tasks are going on in companies and organizations such as procurement, finance and accounting, human resources, supply chain management and IT. These processes require huge amount manpower and effort, so we thought to devise a solution which can proactively interact with the customers and vendors 24/7 and solve their problems with minimal efforts on the company's side.

๐Ÿ’ก Solution

IVR chatbots can be a boon for the companies to manage their work processes easily and smoothly so we developed it. Companies can use it to improve their customer's experience, to generate more sales and build a deeper rapport with customers. They allow your customers to easily interact with your brand through stimulated conversations. It is capable of providing 24h service to their customers. For a good customer experience it provides instant and accurate results to the questions asked by users.

โœจ Presentation

ppt

๐ŸŽฏ Features

Consumers

  • Track Payment Status by orderID
  • Added Authorization security via OTP
  • Explore career opportunities and screening of candidate seeking for a job at ABInBev
  • Report any issue related to website, quality of product, staff / agent behaviour or feedback
  • Schedule Appointment/Call regarding any queries like order, quality of product, delivery, payment issues etc.
  • mail-list signups with the willingness of user inorder to increase the customer engagements
  • Recommending Products and services via querying name, price, alcohol content etc
  • Get Latest ongoing offers on products
  • Responsive Interactive Answers to Frequently asked questions (FAQ) and contact details of department based on the type of query
  • Order a product using chatbot and get e-receipt (Procurement)
  • Know the location of your package (delivery details)

Vendors

  • Increment Collaboration with suppliers and hence increase profits
  • Grab the recent orders by entering the date or month
  • Resetting of database session for each user after some interval of time
  • Get location of any product in warehouse
  • Supplier onboarding
  • Get complete information about any beer with image available at ABInbev

Integrations

  • Multilingual Voice support using speech to text and text to speech API's
  • Multi Chat Channel like sms, chat (Telegram, Whatsapp, Slack, Facebook Messenger, Alexa, Aimybox) and email (non IVR Examples)

๐Ÿค– How we built it

Flow

๐Ÿ™ˆ Mockups

Text to Speech and Speech to Text

Web Chat

Multilingual Support

Web Multiligual

Whatsapp

whatsapp

Telegram

telegram

Slack

slack

Alexa

alexa

๐Ÿ‘ฃ steps to run the project

Run rasa and rasa action server

cd app
pip install requirements.txt

# In one terminal do
rasa run
# In other do
rasa run actions

Run Multilingual React Bot

For Fastapi (backend) server

cd IVR-multilingual
cd api
uvicorn main:app --reload

For react (frontend) app

cd IVR-multilingual
cd frontend
npm install
npm start

Run Voice bot in terminal

cd IVR-terminal
python voice.py

Run Web Chat Voice Bot

cd IVR-web-eng
# and run the html file using live server

๐Ÿ’ป Tech Stack & dependencies

Python, RASA, SQL, gTTS, Twilio, Google Calender API, Google Translator, playsound, prettytable, PyAudio, requests, SpeechRecognition, android, HTML, geopy, opencage, pyauthorize, spacy, smtp, FastAPI

made with ๐Ÿ’• by:

You might also like...
A PyTorch Implementation of End-to-End Models for Speech-to-Text

speech Speech is an open-source package to build end-to-end models for automatic speech recognition. Sequence-to-sequence models with attention, Conne

End-to-End Speech Processing Toolkit
End-to-End Speech Processing Toolkit

ESPnet: end-to-end speech processing toolkit system/pytorch ver. 1.0.1 1.1.0 1.2.0 1.3.1 1.4.0 1.5.1 1.6.0 1.7.1 1.8.1 ubuntu18/python3.8/pip ubuntu18

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit
Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

Espresso Espresso is an open-source, modular, extensible end-to-end neural automatic speech recognition (ASR) toolkit based on the deep learning libra

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform tasks on automatic speech recogniti

In this repository, I have developed an end to end Automatic speech recognition project. I have developed the neural network model for automatic speech recognition with PyTorch and used MLflow to manage the ML lifecycle, including experimentation, reproducibility, deployment, and a central model registry.
Athena is an open-source implementation of end-to-end speech processing engine.

Athena is an open-source implementation of end-to-end speech processing engine. Our vision is to empower both industrial application and academic research on end-to-end models for speech processing. To make speech processing available to everyone, we're also releasing example implementation and recipe on some opensource dataset for various tasks (Automatic Speech Recognition, Speech Synthesis, Voice Conversion, Speaker Recognition, etc).

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.
Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

๐Ÿค— Contributing to OpenSpeech ๐Ÿค— OpenSpeech provides reference implementations of various ASR modeling papers and three languages recipe to perform ta

A demo for end-to-end English and Chinese text spotting using ABCNet.
A demo for end-to-end English and Chinese text spotting using ABCNet.

ABCNet_Chinese A demo for end-to-end English and Chinese text spotting using ABCNet. This is an old model that was trained a long ago, which serves as

Releases(v1.0)
Owner
ARYAMAAN PANDEY
ABInbev Maverick 2.0 Bot-a-thon Winner | Rakuten-Rakathon 2021 Runner Up | AFF Hackathon Winner | Python | JavaScript | Tailwind CSS | ReactJS | ML | NLP
ARYAMAAN PANDEY
Generate a cool README/About me page for your Github Profile

Github Profile README/ About Me Generator ๐Ÿ’ฏ This webapp lets you build a cool README for your profile. A few inputs + ~15 mins = Your Github Profile

Rahul Banerjee 179 Jan 07, 2023
An easy-to-use framework for BERT models, with trainers, various NLP tasks and detailed annonations

FantasyBert English | ไธญๆ–‡ Introduction An easy-to-use framework for BERT models, with trainers, various NLP tasks and detailed annonations. You can imp

Fan 137 Oct 26, 2022
โ˜€๏ธ Measuring the accuracy of BBC weather forecasts in Honolulu, USA

Accuracy of BBC Weather forecasts for Honolulu This repository records the forecasts made by BBC Weather for the city of Honolulu, USA. Essentially, t

Max Halford 12 Oct 15, 2022
Which Apple Keeps Which Doctor Away? Colorful Word Representations with Visual Oracles

Which Apple Keeps Which Doctor Away? Colorful Word Representations with Visual Oracles (TASLP 2022)

Zhuosheng Zhang 3 Apr 14, 2022
Modified GPT using average pooling to reduce the softmax attention memory constraints.

NLP-GPT-Upsampling This repository contains an implementation of Open AI's GPT Model. In particular, this implementation takes inspiration from the Ny

WD 1 Dec 03, 2021
Official source for spanish Language Models and resources made @ BSC-TEMU within the "Plan de las Tecnologรญas del Lenguaje" (Plan-TL).

Spanish Language Models ๐Ÿ’ƒ๐Ÿป Corpora ๐Ÿ“ƒ Corpora Number of documents Size (GB) BNE 201,080,084 570GB Models ๐Ÿค– RoBERTa-base BNE: https://huggingface.co

PlanTL-SANIDAD 203 Dec 20, 2022
TextFlint is a multilingual robustness evaluation platform for natural language processing tasks,

TextFlint is a multilingual robustness evaluation platform for natural language processing tasks, which unifies general text transformation, task-specific transformation, adversarial attack, sub-popu

TextFlint 587 Dec 20, 2022
Train ๐Ÿค—transformers with DeepSpeed: ZeRO-2, ZeRO-3

Fork from https://github.com/huggingface/transformers/tree/86d5fb0b360e68de46d40265e7c707fe68c8015b/examples/pytorch/language-modeling at 2021.05.17.

Junbum Lee 12 Oct 26, 2022
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Hiring We are hiring at all levels (including FTE researchers and interns)! If you are interested in working with us on NLP and large-scale pre-traine

Microsoft 7.8k Jan 09, 2023
Code repository for "It's About Time: Analog clock Reading in the Wild"

it's about time Code repository for "It's About Time: Analog clock Reading in the Wild" Packages required: pytorch (used 1.9, any reasonable version s

52 Nov 10, 2022
Some embedding layer implementation using ivy library

ivy-manual-embeddings Some embedding layer implementation using ivy library. Just for fun. It is based on NYCTaxiFare dataset from kaggle (cut down to

Ishtiaq Hussain 2 Feb 10, 2022
Sentence boundary disambiguation tool for Japanese texts (ๆ—ฅๆœฌ่ชžๆ–‡ๅขƒ็•Œๅˆคๅฎšๅ™จ)

Bunkai Bunkai is a sentence boundary (SB) disambiguation tool for Japanese texts. Quick Start $ pip install bunkai $ echo -e 'ๅฎฟใ‚’ไบˆ็ด„ใ—ใพใ—ใŸโ™ช!ใพใ 2ใƒถๆœˆใ‚‚ๅ…ˆใ ใ‘ใฉใ€‚ๆ—ฉใ™ใŽ

Megagon Labs 160 Dec 23, 2022
Code for Emergent Translation in Multi-Agent Communication

Emergent Translation in Multi-Agent Communication PyTorch implementation of the models described in the paper Emergent Translation in Multi-Agent Comm

Facebook Research 75 Jul 15, 2022
๐ŸŒธ fastText + Bloom embeddings for compact, full-coverage vectors with spaCy

floret: fastText + Bloom embeddings for compact, full-coverage vectors with spaCy floret is an extended version of fastText that can produce word repr

Explosion 222 Dec 16, 2022
๋‰ด์Šค ๋„๋ฉ”์ธ ์งˆ์˜์‘๋‹ต ์‹œ์Šคํ…œ (21-1ํ•™๊ธฐ ์กธ์—… ํ”„๋กœ์ ํŠธ)

๋‰ด์Šค ๋„๋ฉ”์ธ ์งˆ์˜์‘๋‹ต ์‹œ์Šคํ…œ ๋ณธ ํ”„๋กœ์ ํŠธ๋Š” ๋‰ด์Šค๊ธฐ์‚ฌ์— ๋Œ€ํ•œ ์งˆ์˜์‘๋‹ต ์„œ๋น„์Šค ๋ฅผ ์ œ๊ณตํ•˜๊ธฐ ์œ„ํ•ด์„œ ์ง„ํ–‰ํ•œ ํ”„๋กœ์ ํŠธ์ž…๋‹ˆ๋‹ค. ์•ฝ 3๊ฐœ์›”๊ฐ„ ( 21. 03 ~ 21. 05 ) ์ง„ํ–‰ํ•˜์˜€์œผ๋ฉฐ Transformer ์•„ํ‚คํ…์ณ ๊ธฐ๋ฐ˜์˜ Encoder๋ฅผ ์‚ฌ์šฉํ•˜์—ฌ ํ•œ๊ตญ์–ด ์งˆ์˜์‘๋‹ต ๋ฐ์ดํ„ฐ์…‹์œผ๋กœ

TaegyeongEo 4 Jul 08, 2022
A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

A simple Flask site that allows users to create, update, and delete posts in a database, as well as perform basic NLP tasks on the posts.

Ian 1 Jan 15, 2022
Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT.

KR-BERT-SimCSE Implementing SimCSE(paper, official repository) using TensorFlow 2 and KR-BERT. Training Unsupervised python train_unsupervised.py --mi

Jeong Ukjae 27 Dec 12, 2022
Nateve compiler developed with python.

Adam Adam is a Nateve Programming Language compiler developed using Python. Nateve Nateve is a new general domain programming language open source ins

Nateve 7 Jan 15, 2022
Russian words synonyms and antonyms

ru_synonyms Russian words synonyms and antonyms. Install pip install git+https://github.com/ahmados/rusynonyms.git Usage from ru_synonyms import Anto

sumekenov 7 Dec 14, 2022
A Practitioner's Guide to Natural Language Processing

Learn how to process, classify, cluster, summarize, understand syntax, semantics and sentiment of text data with the power of Python! This repository contains code and datasets used in my book, Text

Dipanjan (DJ) Sarkar 1.5k Jan 03, 2023