gladiator07 / jarvis

Personal Voice Assistant made with Python and has a cool looking GUI

Hi 👋, I'm Atharva

Teaching machines to learn, one byte at a time

Welcome to my Profile. This is an overview of all the work I did and I'm planning to do.

---

Contact Me

Hit me up on any platform on my linktree or the ones mentioned below if you want to have a talk!

My Linktree

Other platforms

---

About Me

• 🔭 I am Data Scientist at Wolters Kluwer where I work mostly on Document AI and LLMs, developing end-to-end MLOPs pipelines for extracting information from PDFs.
• 🚀 I am an Ambassador for Weights & Biases
• 👯 I’m looking to collaborate on Kaggle Competitions
• 💪 I love contributing to open-source libraries.
• ⚡ Fun fact: I love to participate in Machine Learning competitions and I'm a Kaggle Competition Expert and highly active there

---

Recent work

I was a speaker at inaugural Weights & Biases MLOps conference (Fully Connected 2023). You can listen to my talk here. [Announcement LinkedIn Post]

---

🛠 My Projects

Click on the project name to directly go to it's GitHub Repository and click demo app to see a live demo of the project

• QA Bot for Gradient Dissent podcast hosted by Weights & Biases: A Question-Answering bot built on top of OPENAI's LLMs and LangChain to provide summary, potential questions on the podcast and the ability to answer any question the user has on the podcast. [demo app]
• Text to Image Synthesis using Attentional GANs - A PyTorch re-implementation of the paper AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adverserial Networks. [demo app]
• Text Summarizer - A transformer based extractive and abstractive text summarizer supporting wide range of input formats. [demo app]
• Healthify - a ML based website which predicts the disease based on the symptoms entered by the patient, also supports several disease diagnosis. [demo app]
• GPU vs TPU comparison for computer vision - compared GPU and TPU for computer vision applications using Google Cloud TPUs and TFRecords data format. [results]
• HARVESTIFY - a ML and DL based website which recommends the best crop to grow, fertilizers to use and the diseases caught by your crops. [demo app]
• JARVIS - a simple voice assistant made using Python [demo video]

---

🏆 Achievements

Click on the competition name to go to it's overview page and click solution + code links to see the approach and source code

• DataSolve 2022 - 1st place finish in the competition organized by Wolters Kluwer - [code]
• Amazon ML Challenge 2021 - 11th place finish among 3200+ teams across India - [solution + code]
• U.S. Patent Phrase to Phrase Matching (Kaggle), identify similar phrases in U.S patents - top 1% (31/1889) [solution] [code]
• Bristol-Myers Squibb – Molecular Translation (Kaggle), translating chemical images to text - silver medal (50/874) - [solution + code]
• Sartorius - Cell Instance Segmentation (Kaggle), detecting single neuronal cells in microscopy images - bronze medal (117/1505) - [code]
• Happywhale - Whale and Dolphin Identification (Kaggle) - bronze medal (132/1588)

---

📝 Open-Source Contributions

• Fixed an example script on HuggingFace 🤗 transformers repository for XLA devices - [PR]
• Made the experiment trackers to launch only on main process in distributed setups on 🤗 Accelerate library - [PR]
• Fixed several examples and removed the check for main process after fixing the tracker's initialization on all processes on 🤗 Accelerate library - [PR]
• Update several 🤗 transformers no_trainer scripts leveraging 🤗 Accelerate to remove the check for is_main_process while initiating trackers by accelerator.init_trackers() as this issue was fixed by me in this PR - [PR]
• Contributed a report to Weights & Biases showcasing the integration of MONAI and W&B - [PR]

TODO: add more contributions

---

✍️ Blogs

• Managing and Tracking ML Experiments - An extensive blog where I've shared my experience and ways to track and manage machine learning experiments effectively for research projects and Kaggle competitions (w/ Weights & Biases and Hydra)
• HuggingFace is all you need for NLP and beyond - A tutorial/blog on HuggingFace ecosystem and how to use and customize 🤗 datasets and 🤗Trainer for all of your NLP problems.
• 3D Segmentation with MONAI and PyTorch Supercharged by Weights & Biases - A W&B report showcasing the integration of MONAI and W&B for medical imaging. Shows how to efficiently track experiments, perform error analysis, artifacts versioning and much more using the rich suite of W&B features.
• DeepMind Flamingo: A Visual Language Model for Few-Shot Learning - A Weights & Biases report explaining the paper Flamingo: A Visual Language Model for Few-Shot learning by DeepMind. This report is also featured on Two Minute Papers YouTube Channel here.
• Hugging Face Accelerate Super Charged With Weights & Biases - a Weights & Biases report to show how you can supercharge your raw PyTorch code to train on distributed systems with Hugging Face Accelerate and seamlessly integrate Weights & Biases into your workflow.
• SetFit: Efficient Few-Shot Learning Without Prompts - this report dives into HuggingFace, Intel Labs, and UKP Lab's recent paper on Efficient Few-Shot Learning Without Prompts. SetFit exceeds prior methods in accuracy and efficiency with just 8 labeled samples.
• Is PyTorch 2.0 Faster Than PyTorch 1.13? - this report compares the PyTorch 1.3 and the newly announced PyTorch 2.0, with it's highlight being the torch.compile mode which provides significant speed gains .
• BLIP-2: A new Visual Language Model by Salesforce - this reports explores BLIP-2, a new Vision Language Model by Salesforce which beats the previous state-of-the-art Flamingo on various multimodal tasks.
• Building a Q&A Bot for Weights & Biases' Gradient Dissent Podcast using LangChain and OpenAI - in this article, we explore how to utilize OpenAI's ChatGPT and LangChain to build a Question-Answering bot for Weights & Biases' podcast series, Gradient Dissent.

---

💪 Currently working on

• Kaggle competitions and Open-Source :)

---

jarvis's Issues

ImportError: cannot import name 'config' from 'Jarvis.config' (unknown location)

Closes

It closes Every time i say something how do i fix

im using pycharm btw

Jarvis

re.search error

when Jarvis finished his greeting the program goes close. and show the error

======================================================

I keep getting the message "ModuleNotFoundError: No module named 'speech_recognition'" and it wont launch the program.

Jar1

it closes everytime i say something

FileNotFoundError: [Errno 2] No such file or directory: 'credentials.json'

You said: jarvis take a screenshot
Traceback (most recent call last):
File "c:\Users\venky\Downloads\JARVIS-master\JARVIS-master\main.py", line 108, in run
self.TaskExecution()
File "c:\Users\venky\Downloads\JARVIS-master\JARVIS-master\main.py", line 231, in TaskExecution
obj.google_calendar_events(command)
File "c:\Users\venky\Downloads\JARVIS-master\JARVIS-master\Jarvis_init_.py", line 126, in google_calendar_events
service = google_calendar.authenticate_google()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "c:\Users\venky\Downloads\JARVIS-master\JARVIS-master\Jarvis\features\google_calendar.py", line 48, in authenticate_google
flow = InstalledAppFlow.from_client_secrets_file(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\venky\AppData\Local\Programs\Python\Python311\Lib\site-packages\google_auth_oauthlib\flow.py", line 198, in from_client_secrets_file
with open(client_secrets_file, "r") as json_file:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
FileNotFoundError: [Errno 2] No such file or directory: 'credentials.json'

The run button is not showing

The run button is not showing

speech recognition not found

File "d:\Bhavya study\Bhavya study docs\Web Development\JARVIS-master\Jarvis_init_.py", line 1, in
import speech recognition as sr
ModuleNotFoundError: No module named 'speech recognition'
PS D:\Bhavya study\Bhavya study docs\Web Development\JARVIS-master>

How do I get the grafics?

this happens after the intro

File "c:\users\lucas\appdata\local\programs\python\python39\lib\re.py", line 202, in search
return _compile(pattern, flags).search(str)
TypeError: expected string or bytes-like object

blank screen

no buttons are shown when i run the program. If anyone can help

Changing The Format Of If-Else Loops To Make It More Convenient

We Can Apply This Kind (Given Below) Of Format Instead Of If-Else Loops as these are more convenient for creating conversations and I am Planning To Add A GUI Like Cortana.

It Would Be My Honor To Contribute, Please Allow Me To Contribute!

Regards
Arnav Singh

            for text in Greetings1_In:
                if str(text) in Query:
                    Random_Number = Rnum(0, len(Greetings1_Out)) #Rnum Is A Function for getting A random number!
                    Speak(Greetings1_Out[Random_Number])   
                    break

            for text in Greetings2_In:
                if str(text) in Query:
                    Random_Number = Rnum(0, len(Greetings2_Out))
                    Speak(Greetings2_Out[Random_Number])   
                    break

Hashah2311

Hi everyone i am Hashah2311.
I am posting this issue because i thought that you all can check my JARVIS Bot.
Please check it out!
Thanks

cannot import JarvisAssistant from Jarvis

I also checked if there is spelling mistake or what. but this shitty issue comessssss!!!!!!!!!!!!!! I am exhuasted!!!!!!! plz helppppp

the buttons are not vissible

the ui window occupies the whole space in the desktop .
the RUN and EXIT buttons are not visible .

i use the code in pycharm and the result is..

what's the problem?

Don't show buttons.

when I run that program paused screen appear and don't visible any type of button on screen.

requirements.txt file is missing

there is no requirements.txt file in the project