[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8},"actionData","errors","root",{"_133":134,"_135":136,"_137":138},"routes/item",{"_9":10,"_11":12},"item",{"_13":14,"_15":16,"_17":18,"_19":20,"_21":-5,"_22":23,"_24":25,"_26":27,"_28":29,"_30":29,"_31":32,"_33":34,"_35":36,"_37":38,"_39":40,"_41":42,"_40":43,"_44":45,"_46":47,"_48":49,"_50":51,"_52":53,"_54":55,"_56":57,"_58":38,"_59":60,"_61":62,"_63":38,"_64":65},"expiresAt",1793996995000,"id","gywh7ruusoce7bv0kgauof285","title","Confucius4-R2T2 from NetEase Youdao tops Hugging Face's ASR Trending list","originalTitle","The way these guys are doing streaming speech recognition is really cool.","summary","NetEase Youdao's Confucius4-R2T2 reached No. 1 on Hugging Face's ASR Trending list within four days of release, according to Santiago. The model has more than 200K cumulative downloads worldwide, including quantized versions. Santiago says he read the paper, which is linked, but the post gives no further details.","reason","source",{"_78":93,"_132":40},"links",{"_65":131},"publishedAt","2026-11-06T17:15:30.000Z","discoveredAt","2026-11-06T17:46:17.484Z","timelineAt","category","paper","tags",[72,74],"score",34,"selected",false,"channel","x","story",{"_85":86,"_15":87},{"_92":93,"_94":47,"_95":96,"_97":98,"_99":60,"_100":101,"_102":-5,"_103":104,"_105":-5,"_106":107},"readingMode","full","author","svpino","body",{"_88":-5,"_65":89,"_90":-5,"_91":60},"outline",[],"relatedStories",[84],"topics",[82,83],"tagTopics",{"_72":73,"_74":75},"indexable","markdownAvailable",true,"group",{"_66":67,"_68":69,"_70":71},"hasTranslation","bodyLanguage","original","factId","fLbNXKEfsW8s","reportCount",1,"additionalSourceCount",0,"Paper/Research",{"_76":80,"_78":81},"Voice",{"_76":77,"_78":79},"slug","voice","name","Voice & audio","papers","Papers & research",{"_76":77,"_78":79},{"_76":80,"_78":81},{"_85":86,"_15":87},"publicId","6599523f-dcbe-4ffc-85d2-fe19651c9097","NetEase Youdao's Confucius4-R2T2 tops Hugging Face's ASR Trending list","zh","

The way these guys are doing streaming speech recognition is really cool.

#1 on Hugging Face's ASR Trending list: Confucius4-R2T2 from @NetEaseYouDaoAI. It hit #1 within 4 days of release.

It now has 200K+ cumulative downloads worldwide, including quantized versions.

I read their paper, and here is what you should know:

https://arxiv.org/pdf/2611.06043

","zhKind","complete","authorName","Santiago","handle","avatarUrl","/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fprofile_images%2F1581385027757264898%2Fj5GjtUiq_bigger.jpg&mode=avatar&exp=1794182400&sig=4508c74c77a00f9f","avatarSrcSet","/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fprofile_images%2F1581385027757264898%2Fj5GjtUiq_bigger.jpg&mode=avatar-48&exp=1794182400&sig=2de665eccdea781d 48w, /api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fprofile_images%2F1581385027757264898%2Fj5GjtUiq_bigger.jpg&mode=avatar&exp=1794182400&sig=4508c74c77a00f9f 96w","verified","lang","en","quoted","media",[118],"replyTo","metrics",{"_108":109,"_110":111,"_112":113,"_114":115,"_116":117},"replies",14,"reposts",2,"likes",8,"views",2097,"countedAt","2026-11-06T17:46:15.875Z",{"_119":120,"_121":122,"_123":124,"_125":126,"_127":128,"_129":-5,"_130":-5},"kind","image","url","/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWdTrfjbUAAZFW0.jpg&mode=full&exp=1794182400&sig=a3dc2c493dc13be7","srcSet","/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWdTrfjbUAAZFW0.jpg&mode=thumb&exp=1794182400&sig=05b9289efead06a4 720w, /api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWdTrfjbUAAZFW0.jpg&mode=image-1200&exp=1794182400&sig=fbeb28b0ba13d871 1200w, /api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWdTrfjbUAAZFW0.jpg&mode=full&exp=1794182400&sig=a3dc2c493dc13be7 1600w","width",1290,"height",1098,"alt","poster","https://x.com/svpino/status/2118754159281459416","label","changelogVersion","2026-10-20T07:32","release","2d11284a1afbc47f7df884f9aec30f04bbc51d6c","analytics",{"_139":140,"_141":142},"key","phc_7eKgPSslcg5Gf87YcEkca6iJdjuyArh07WPfBVxHREv","host","https://eu.i.posthog.com"]