IndexMapAnti-DoomscrollAbout
Model FamilyCross-ModalLLM

Whisper & Speech Recognition (ASR)

Also known as: Whisper · OpenAI Whisper · Whisper large-v3 · Distil-Whisper · ASR

Plain English

OpenAI's open-weight speech recognition model family that turns spoken audio in nearly a hundred languages into accurate text transcripts and English translations.

Technical Overview

Whisper processes 30-second log-Mel spectrogram windows through a convolutional stem and an encoder-decoder Transformer trained with multitask special tokens for transcription, voice activity detection, language identification, word timestamps, and X -> en translation. Speculative Distillation & Synthetic Data variants (Distil-Whisper and large-v3-turbo) prune decoder layers from 32 to 2–4 for 5x+ lower latency.

Timeline (4)

RSS
  1. 2022

  2. 2023

  3. 2024

    Release

    OpenAI released Whisper large-v3-turbo (809M parameters), reducing the large-v3 decoder from 32 layers to 4 layers to deliver over 5x faster transcription on whisper.cpp and cloud endpoints with negligible accuracy loss.

  4. 2025

See also (9)

Open full graph
4 more connections