Cross-platform, customizable ML solutions for live and streaming media.
- mediapipe
- c-plus-plus
- computer-vision
- deep-learning
47,133 repositories indexed
1–22 of 22 · Most stars
Cross-platform, customizable ML solutions for live and streaming media.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
Production ready toolkit to run AI locally
:dancer: Real-time single person pose estimation for Android and iOS.
BYOK voice recording companion with ASR transcription, speaker diarization, AI summaries, and local ASR endpoint support.
Android Input Method Editor (IME) based on Whisper
🗣 An overlay that gets your user’s voice permission and input as text in a customizable UI
A tool for quantitative risk analysis of Android applications based on machine learning techniques
⚡️ Capacitor plugin for synthesizing speech from text.
How to create a Cartoonizer Android app with TensorFlow Lite models.
Examples of Tensorflow Lite on Android
How to create Selfie2Anime from tflite model to Android.
Ultra high-performance secp256k1 ECC engine | Python, Node.js, Rust, Go, C#, Swift, Java bindings | CUDA, Metal, OpenCL GPU | ECDSA, Schnorr, FROST, MuSig2, BIP-352 | 15+ platforms
📌This repo contains the kotlin implementation of TensorflowLite Example Android Apps🚀
Flutter TF Segmentation is an example app that uses Flutter for the ios/android app and uses TensorFlow Lite for Image segmentation.
Java Scientific Computing Library - Signal Processing, FFT, Filters, PSD, DCT, SciPy-like APIs for JVM & Android used in Machine Learning and Data Science.
Profile your Tensorflow Lite model on-device
MIRNet model is used to enhance a low-light image. Implemented MIR-Net model with TF-Lite.
Tensorflow style transfer in video
An Icon classifier made with TFLite Model Maker and deployed to Android with ML Model Binding.