72 results for “topic:on-device-ml”
Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt
Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement (NeurIPS 2020)
A custom RAG pipeline for multi-document QA from PDF/DOCX documents, in Android
This repository contains notebooks that show the usage of TensorFlow Lite for quantizing deep neural networks.
This is a web demo for camera-based PPG sensing (rPPG).
An Android app running inference on Depth-Anything and Depth-Anything-V2
Embeddings from sentence-transformers in Android! Supports all-MiniLM-L6-V2, bge-small-en, snowflake-arctic, model2vec models and more
Run LLMs, ASR and TTS locally in your app (Rust core, iOS/Android/Flutter/Unity)
High-performance on-device vector search engine for Expo & React Native. Powered by C++ JSI and USearch (HNSW) for sub-millisecond similarity matching.
A curated collection of LLM-powered Flutter apps built using RAG, AI Agents, Multi-Agent Systems, MCP, and Voice Agents.
Object detection inference with Roboflow Train models on NVIDIA Jetson devices.
On-Device Static Sentence Embeddings in Swift/iOS/macOS apps
Real-time OCR app for Android with PP-OCRv5 and LiteRT.
Approach to implementing distributed training of an ML model: server/device training for iOS and macOS.
A macOS Tahoe app for transcribing audio/video files using Apple's on-device Speech APIs (SpeechTranscriber & SpeechAnalyzer)
Privacy-first personal health journal with experimental AI features. Track medications, journal symptoms, and explore on-device ML (for educational purposes)
[NeurIPS'24] DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
🚀 Production-ready Android ML Kit showcase featuring barcode scanning & text recognition with 100% test coverage. Built with Jetpack Compose, CameraX, MVVM architecture, and Hilt DI.
Control your computer using hand gestures with AI, using Google's MediaPipe and OAK-D Lite camera.
Android library that provides tools for ML inference, semantic search and indexing, media processing and efficient batch processing.
Machine learning components for the Defndr SMS spam filter app. https://dro1d.org
On-device scanner for identifying sensitive content within the photo library. Utilizes Apple’s SensitiveContentAnalysis framework for local detection of explicit media. Privacy-first, zero-cloud architecture. https://dro1d.org
Reference implementation: run any huggingface tokenizer in Android (rust).
Project Agora: MVP of the Concordia framework. An ethical, symbiotic AI designed to foster and protect human flourishing.
End-to-end on-device federated learning, "An On-Device Federated Learning System for SMS Spam Classification", IEEE MIT URTC 2022
🕰️ Transform your health data into a private longevity dashboard that shows real-time life expectancy changes based on daily habits.
🕰️ LifeDelta - Dynamic Longevity Coach. Gain days you can see with on-device ML survival analysis, habit impact tracking, and AR food scanning. Privacy-first iOS app with HealthKit integration.
Voice notes app for sales with speaker diarization and transcription. Supports offline on-device speech recognition with Japanese language. Features real-time audio level visualization and background recording.
Swift library for Voice Activity Detection (VAD) using NVIDIA NeMo MarbleNet model converted to CoreML. Detect speech segments in real-time on iOS/macOS with high accuracy and low latency.
A minimalistic Android app showcasing semantic search using ObjectBox and Lucene KNN, leveraging the MiniLM-L6-V2 embedding model and bert_vocab.txt for efficient retrieval.