Activity
Stars and mentions · Last 30 days, Oct 6 – Nov 4
Top repositories
netease-youdao’s repositories ranked by new stars, as on trending.
Contributes to
Repositories outside netease-youdao’s account where netease-youdao opened or reviewed pull requests in the past 365 days.
Who noticed netease-youdao
Everyone who starred or forked netease-youdao’s repositories since the archive began in 2011.
Notable accounts
Ordered by the stars their own repositories have received.
Biggest fans
Accounts that starred the most of these repositories.
Breakout weeks
Each repository’s best week of new stars, with the release published around it.
Achievements
Awards earned by the repositories netease-youdao owns. Select an award to embed its badge.
- Gold
- 01st place finishes
- Silver
- 22nd place finishes
- Bronze
- 03rd place finishes
- Awarded repositories
- 1Owned by netease-youdao now
Repositories
Ordered by gold, then silver, then bronze.
- EmotiVoiceBest: 2nd by stars, 1,228 stars020
Every award
Top-three finishes of these repositories in completed trending days and weeks, newest first.
A repository earns an award for finishing first, second or third in a completed trending day or week, ranked by new stars, new forks or pull request authors. Awards follow a repository through renames and transfers and count toward its current owner. Weeks run Monday to Sunday, UTC.
Mentions
Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription Streaming speech recognition is increasingly consumed by machines, such as translators and voice agents, that act on each token as it appears. A token that is later revised costs wasted work or a wrong action. In this work, we present Confucius4-R2T2 (short for Real Real-Time Transcription), a stable-prefix streaming ASR model that never modifies its earlier output while maintaining high accuracy and low latency. R2T2 is obtained by post-training Qwen3-ASR-1.7B on 1,500 hours of Chinese and English audio while freezing its pre-trained audio encoder and projector. The adaptation is based on the concept of Longest Stable Prefix (LSP), a new notion that we introduce in this work. We prove that LSP is monotone under the prefix order, consistent with the full-audio output, and maximal among labels that equal a whole earlier output. Learning from LSP labels converts a full-context model into a stable-prefix streaming one without any architectural change. Extensive evaluations show that R2T2 brings streaming recognition close to the base model's full-context quality while delivering stable text with low emission lag. Its gains extend beyond the post-training languages, demonstrating a practical path from full-context ASR to stable streaming. We open-source the model weights and code at huggingface.co and netease-youdao/Confucius4-R2T2. Comments: 30 pages, 6 figures, 8 tables. Code and model weights available at netease-youdao/Confucius4-R2T2 and huggingface.co
Sometimes the best prompt is an arrow. LobsterAI’s Oct 23 update adds image annotations and region selection. Conversation snapshots keep the source image and those markings. Useful for “change this bit” without a paragraph explaining which bit. github.com/netease-youdao/LobsterAI/releases/tag/…
办公软件的重复活干到手软？试试 LobsterAI，网易有道开源的桌面级 AI Agent，文档表格 PPT 都能替你干完，GitHub 已经 6100+ star 了。 netease-youdao/LobsterAI
Excel 扔进去一句话，算完还给你画好图。LobsterAI 6 千星，网易有道开源的桌面智能体：表格拖进去用中文说「按月份汇总销售额」它自己算，算完直接出图表还能追问，也读文档写报告，装在本地不上传。 netease-youdao/LobsterAI
EmotiVoice is an open source text to speech engine from NetEase Youdao. It speaks Chinese and English with over 2,000 voices, and a short style prompt like happy or sad shifts the pitch, speed, and energy of the audio. netease-youdao/EmotiVoice t.co