@weiting_nlp : Is your model struggling with high latency and huge memory costs for real-time sequence processing? 🚀 Introducing STAR: A transformer-based model for streaming seq2seq transduction with compression. arxiv.org/abs/24502.01172 #NLProc #Streaming #Seq2seq #Compression #SpeechToText • TwiCopy

Weiting (Steven) Tan

@weiting_nlp

+ Follow

Ph.D. student at @jhuclsp, Research Scientist Intern @AIatMeta | Prev @AIatMeta @Amazon Alexa AI

ID: 1414244140544573442

linkhttps://steventan0110.github.io/ calendar_today11-07-2021 15:24:25

46 Tweet

133 Followers

220 Following

Weiting (Steven) Tan

@weiting_nlp

8 months ago

Is your model struggling with high latency and huge memory costs for real-time sequence processing? 🚀 Introducing STAR: A transformer-based model for streaming seq2seq transduction with compression. arxiv.org/abs/2402.01172 #NLProc #Streaming #Seq2seq #Compression #SpeechToText