// ◉ Multimodal & Vision

Whisper

General speech recognition trained on 680K hours of weakly labeled web audio.

Whisper 弱监督语音识别 2022 Foundational core

IN PLAIN WORDS

An encoder–decoder Transformer from log-Mel spectrograms to text, with special tokens for language, task and timestamps. Massive diverse data gives robustness.

Used in: Subtitles, meeting transcription, voice assistants

TIMELINE · prerequisites → this → what builds on it

2017 Transformer &…2022 Whisper

01Original paper

Robust Speech Recognition via Large-Scale Weak Supervision

Alec Radford, Jong Wook Kim, Tao Xu, et al. · 2022

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Transformer & Self-Attention

Whisper

Then you can learn

Nothing in the atlas builds on it yet

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Reference code

github.com ↗EN

04Where the course teaches it

U73 Speech, Video & World Models Whisper, video diffusion (Sora-style DiT), 3-D reconstruction, world models, Dreamer and Genie. 8 h10 algorithms4 papers

On learning paths:Generative Models & Frontier Research

For AI / data

Verification: verified, checked 2026-10-21.
JSON: /api/learn/algorithms.json (id: whisper)