faster-whisper

High-performance, CTranslate2-based reimplementation of OpenAI's Whisper model: up to 4x faster transcription with lower memory use.

Faster-Whisper is your optimized solution for speech-to-text, leveraging CTranslate2 (a fast inference engine for Transformer models) to reimplement OpenAI's Whisper. This architecture delivers a significant performance boost: expect transcription speeds up to four times faster than the original `openai/whisper` implementation while maintaining comparable accuracy. Efficiency is key here: the model also uses less memory and supports 8-bit quantization, further improving performance on both CPU and GPU hardware. It's the go-to backend for high-speed, resource-conscious ASR (Automatic Speech Recognition) applications.

https://github.com/SYSTRAN/faster-whisper