GitHub Trends
10.1K subscribers
15.3K links
See what the GitHub community is most excited about today.

A bot automatically fetches new repositories from https://github.com/trending and sends them to the channel.

Author and maintainer: https://github.com/katursis
Download Telegram
#swift #inference #ios #macos #pretrained_models #speech_recognition #swift #transformers #visionos #watchos #whisper

WhisperKit is a tool that helps your Apple devices recognize speech from audio files or live recordings using OpenAI's Whisper model. It works locally on your device, which means it doesn't need internet connection once set up. To use it, you can add WhisperKit to your Swift project easily through the Swift Package Manager or install a command-line version using Homebrew. This tool is beneficial because it allows you to transcribe audio quickly and efficiently right on your device, making it useful for various applications like voice assistants or transcription services.

https://github.com/argmaxinc/WhisperKit
#python #asr #automatic_speech_recognition #conformer #e2e_models #production_ready #pytorch #speech_recognition #transformer #whisper

WeNet is a powerful tool for speech recognition that helps turn spoken words into text. It's designed to be easy to use and works well in real-world situations, making it great for businesses and developers. WeNet provides accurate results on many public datasets and is lightweight, meaning it doesn't require a lot of resources to run. This makes it beneficial for users who need reliable speech-to-text functionality without complex setup or maintenance.

https://github.com/wenet-e2e/wenet
#cplusplus #ai #automation #cross_platform #linux #live #llm #mac #macos_app #meeting_minutes #meeting_notes #recorder #rust #whisper #whisper_cpp #windows

Meetily is an AI meeting assistant that helps teams by capturing and transcribing meeting audio in real-time. It generates meeting summaries and action items, making it easier to review and follow up on discussions. Meetily focuses on privacy by processing data locally on your device, ensuring your meeting content remains secure. It's cost-effective, works offline, and supports multiple platforms. Users can customize it to fit their needs, making it a convenient tool for efficient meeting management. This helps teams focus on discussions without worrying about taking notes manually.

https://github.com/Zackriya-Solutions/meeting-minutes
👍3
#typescript #ai #cross_platform #desktop #openai #rust #transcribe #whisper

You can use Vibe to easily transcribe audio and video files on your own computer without needing the internet. It works offline using OpenAI’s Whisper engine, so your data stays private and never leaves your device. Vibe supports many languages, multiple file formats like SRT for captions, and can transcribe from system audio, microphone, or popular websites. It runs on Mac, Windows, and Linux, and offers features like batch transcription, real-time preview, translation, and AI-powered summaries. This helps you quickly get accurate transcripts while keeping your information secure and under your control.

https://github.com/thewh1teagle/vibe