MultimodalOpenAI

OpenAI open-sources Whisper

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Open-sourced Whisper — weakly supervised training on 680,000 hours of multilingual data

Why it matters

Commoditized multilingual ASR, making speech a standard input to LLM pipelines

Source — Primary sources first; secondary reports are labelled “Press”

Officialopenai.comhttps://openai.com/index/whisper/

Added in Week 35, 2026 · See that week

On the map — ⑦ Multimodal line

  1. Previous stopLatent Diffusion
  2. This record · stopWhisper
  3. Next stopGPT-4V
See it on the map

Same week

Toy Models of SuperpositionPaper

Nearby on the same axis

Stability AI and CompVis release Stable Diffusion v1.4 weightsOfficialMidjourney launches open betaPressFlamingoPaperLLaVAPaper