Skip to content
Hugging Face Blog·· 2025-05-13AI score36

Hugging Face Launches a Blazing-Fast Whisper Transcription Endpoint Based on vLLM, with 8× Performance Improvement

Blazingly fast whisper transcriptions with Inference Endpoints

AI briefing

Hugging Face launches a new OpenAI Whisper deployment on Inference Endpoints, implemented with vLLM, achieving nearly 8× improvement in RTFx over the previous version with no loss in transcription quality.

Open original huggingface.co