There are 11 repositories under on-device topic.
DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.
Awesome LLMs on Device: A Comprehensive Survey
AubAI brings you on-device gen-AI capabilities, including offline text generation and more, directly within your app.
On-device CocoaLumberjack console with support for search, adjust levels, copying and more.
Precision genomics for everyone, everywhere. Powered by private AI.
The baseline project for inferencing various Pose Estimation tflite models with TFLiteSwift on iOS
Convmelspec: Convertible Melspectrograms via 1D Convolutions
Personalized machine learning on the smartphone
Eris is a private AI chat application that runs entirely on your device using Apple's MLX framework. Named after the dwarf planet that challenged our understanding of the solar system, Eris challenges the notion that AI must live in the cloud.
Real-time speech enhancement mobile app using Nested U-Net
Official repo for Jesture AI SDK: Real-time On-device Hand Gesture Control
Custom implementation of Apple Intelligence features
A proof-of-concept app using KeenASR SDK on Android. WE ARE HIRING: https://keenresearch.com/careers.html
iBeta (Level 2) Certified, Single-Image Based Face Liveness Detection (Face Anti Spoofing) Server SDK
Real-world context insights SDK for Swift apps, enhancing user experience and engagement with a privacy-first approach
Unity package for using Spark-TTS on-device models. This is a C# port of https://github.com/SparkAudio/Spark-TTS by SparkAudio team and uses converted ONNX models instead of the PyTorch models in the original repo
Lightweight on-device keyword spotting engine for iOS using CoreML and real-time audio streaming.
Adaptive Fall Detection on the Edge using MobiAct dataset
Real-world context insights SDK for React Native apps, enhancing user experience and engagement with a privacy-first approach
Proof-of-concept app that showcases use of KeenASR SDK in a Swift app. WE ARE HIRING: https://keenresearch.com/careers.html
Combining the power of MobileNetV2 with the privacy of on-device learning. Benefit from real-time updates and efficient image processing, all while ensuring your data remains securely on your device. Experience precision, speed, and trust with PixeLearner.
[IEEE TII] On-Device Saliency Prediction Based on Pseudoknowledge Distillation
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.
LiveTalk is a unified, high-performance talking head generation system that combines the power of LivePortrait and MuseTalk open-source repositories. The PyTorch models from these projects have been ported to ONNX format and optimized for CoreML to enable efficient on-device inference in Unity.
This Android app leverages a TensorFlow Lite model for on-device classification of social media posts into 11 categories, including technology, sports, finance, and more. Built with Kotlin and Jetpack Compose, it ensures efficient, privacy-focused inference without server dependencies.