Saltb0xApps

Quick-Compose

Quick compose lets you post to facebook/tweet right from an iOS 8 notification center widget with its own built in keyboard like the iOS 6 social widget apple later on removed.

Friendbox

Show Facebook home feed in iOS 8 widget along with ability to like it directly, or open in Facebook app. Uses read_stream key so can’t be published on App Store.

HumanPoseEstimation

HumanPoseEstimation for iOS using CoreML

Beats-Maker

SwipeType

SwipeType for < iOS 7. This added keyboard shortcuts like select all, copy, paste, etc. to the default iOS keyboard (before apple introduced the custom keyboard APIs)

AI-Companion

Training a16z's AI Companion project for a custom personality

Pixl-NFTs-SDK

Mint NFTs & Create Smart Contracts on Polygon from any iOS app without any blockchain knowledge

Depth-Segmentation

Use truedepth camera for depth segmentation & replace the background with a black color background

Pixl-Discovery-NFTs-SDK

Discover NFTs on the Ethereum/Polygon blockchain around the world in AR with persistence

Pixl-Placement-NFTs-SDK

place nfts from the polygon blockchain anywhere in AR with persistence

Pixl-Portals-NFTs-SDK

open portals with nfts from the polygon blockchain anywhere in AR

Pixl-SDKs-Example-App

Example app that shows how to use the minting, discovery & placement SDKs from Pixl

ai-audio-startups

Community list of startups working with AI in audio and music technology

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

audiotools

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

instruct-MusicGen-vocals

modifying musicgen instruct to handle vocals with lyrics conditioning

optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

parler-tts

Inference and training library for high-quality TTS models.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

versatile_audio_super_resolution

Versatile audio super resolution (any -> 48kHz) with AudioSR.

WhisperFusion

WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.