90% savings using optimised Whisper API and distributed computing Posted by svij137 on Tuesday April 18, 2023 @09:36PM from the qblocks.cloud dept. https://www.qblocks.cloud/blog/ultra-low-cost-transcribing-openai-whisper ( 1 comment | on HN )
TL;DR :
1.CTranslate2 is used to optimize the OpenAI Whisper model for efficient inference with Transformer models.
2. It can be easily installed on a Q Blocks GPU instance with a simple command.
3. The optimized Whisper model can be run on a Q Blocks decentralized 3090 GPU instance.