On-device speech SDK for Android — ASR, TTS, VAD, and noise cancellation powered by ONNX Runtime with Qualcomm NNAPI acceleration

DeepLab V3 TFLite models that be fully delegated to NNAPI

Run 2D convolution layer with NNAPI

Rust bindings to the Android NNAPI

This Android application demonstrates image classification using a pre-trained machine learning model to classify fruits into categories such as Apple, Banana, and Orange. The model is integrated into the app using TensorFlow Lite, with optimization for inference using NNAPI (Android Neural Networks API) for improved performance on Android devices.

Android NNAPI Supporting Operations

Assignments Completed during CSE535:Mobile Computing Course in IIITD during Winter 2024 Semester. Professor: Arani Bhattacharya

Low Latency Deep Learning on Smartphones using TensorFlow Lite and CoreML

Android dog breed classification app using Kotlin, Jetpack Compose, and TensorFlow Lite, with on-device inference and a simplified public demo UI.

Android-first React Native ONNX Runtime bindings with Nitro Modules, backend selection, tensor inference, benchmarking, and experimental QNN diffusion pipeline helpers.

Offline Android audio/video transcription with sherpa-onnx Whisper, punctuation-first subtitles, model management, NNAPI acceleration, and SRT/VTT/TXT export.

Net Tools in Python: networking tool in python that allows users to read from an input file with hostname and MAC address and update the system's host file accordingly. It was built to discover, map and maintain IP-Hostname mapping in a local network.

Open source mobile deep learning model for COVID-19 detection with POCUS