Yudong‘s Blog

AI Research & Engineering: RecSys, Search, NLP, Generative AI and Beyond

Tag Whisper

Whisper Explained：端到端语音识别新范式深度解读

Whisper Explained: OpenAI's end-to-end speech recognition model — architecture, algorithm, and source code deep dive

本文是一篇详细的 Whisper 技术拆解：从整体架构、音频预处理、Multitask 训练范式，到 PyTorch 源码逐段精读和性能 / 生态对比，并配 SVG 原理图、参数表与可运行代码。

Loading

2025-01-17 0

© 2026 Yudong‘s Blog — Powered by WordPress

Theme by Anders Noren — Up ↑