Fill IT

Created by team Mixed Intelligence on August 26, 2024
IBM GraniteOpenAI

Project Name: FILL IT Author: Umar Majeed Description: FILL IT is an automated system designed to streamline data entry processes. The project utilizes the Whisper model for transcribing audio recordings into text and the IBM Granite model for extracting information and filling out forms. The workflow involves: Audio Transcription: Converts audio files (e.g., WAV, MP3) into text using the Whisper model. Text Extraction: Extracts text and questions from a PDF form. Form Generation: Uses the IBM Granite model to generate completed form data based on the transcribed text and extracted questions. Due to technical issues, I was unable to deploy the application before the submission deadline. I am actively working on deploying it and will make it available soon. For now, I am submitting the project in its current state. The Kaggle notebook detailing the implementation is shared for reference.

Category tags:
GithubPresentationDemo
Explore more applications

Toddle AI

Toddle AI is a privacy-first Android app that analyzes toddler walking videos on-device, checks capture quality, measures gait patterns from pose landmarks, and lets parents ask a local AI assistant to explain the result

Toddle AI

Qualcomm Snapdragon

Lantern: Model anything

Lantern turns a smartphone into an AI-powered 3D scanner. Using on-device AI with ExecuTorch, it generates accurate 3D meshes in real time without cloud processing, LiDAR, or external hardware, making 3D scanning fast, private, and accessible.

Lantern

Meta ExecutorchClaude CodeQualcomm Snapdragon

Memory Recall Assistant

A private, on-device memory assistant for cognitive decline. Using ExecuTorch on Snapdragon 8 Elite NPU, it identifies faces, transcribes conversations via Whisper, and generates warm recall cues via Llama 3.2 1B - fully offline, zero cloud.

Synapse Riders

Meta ExecutorchQualcomm SnapdragonWhisperLlama 3.2AI StudioAnthropic ClaudeGithub Copilot

SafeScreen AI

An on-device visual safety layer that helps protect people from explicit, abusive, and manipulated media before they interact with it.

SafeScreen AI

Qualcomm SnapdragonClaude Code

PrivateDoc

PrivateDoc is an offline, on-device visual assistant that uses ML Kit OCR, ExecuTorch, MiniLM, and Llama 3.2 to scan, index, and answer questions about private documents. Its strict RAG pipeline provides source-grounded answers. Powered by SnapDragon.

Edge Faithful

Qualcomm SnapdragonGithub CopilotMeta ExecutorchLlama 3.2