Repository History
3 repositories tagged with whisper
Insanely Fast Whisper: Blazing-Fast Audio Transcription CLI
Insanely Fast Whisper is an efficient command-line interface for transcribing audio files on-device using OpenAI's Whisper models. Powered by Hugging Face Transformers, Optimum, and Flash Attention 2, it delivers blazing-fast performance, capable of transcribing hours of audio in just minutes. This tool provides a streamlined and optimized solution for high-speed speech-to-text conversion.
Whisper Web: ML-Powered Speech Recognition Directly in Your Browser
Whisper Web brings powerful, ML-powered speech recognition directly to your browser, leveraging ? Transformers.js. This innovative project allows for client-side audio processing, offering privacy and efficiency without relying on cloud services. It even includes experimental WebGPU support for accelerated performance.
whisper.cpp: High-Performance Speech Recognition with OpenAI's Whisper Model
whisper.cpp is a high-performance C/C++ port of OpenAI's Whisper automatic speech recognition (ASR) model. It offers efficient, dependency-free inference across a wide range of platforms, from desktop to mobile and embedded devices. This project enables fast, local speech-to-text capabilities, making advanced AI accessible for various applications.