A Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2211.02499/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Weakly-Supervised Streaming Multilingual Speech Model with Truly Zero-Shot Capability — mentioned by woodsonhttps://news.ycombinator.com/item?id=35368033urn:hackerpapers:mention:2211.02499:35368033Thu, 30 Mar 2023 04:37:15 GMT<p>Whisper doesn’t do streaming transcription or translation. It’s one of its architectural disadvantages over more commonly used ASR approaches, such as transducers (see e.g. Microsoft Research’s system trained on ~350k hours that does streaming transcription and translation: https://arxiv.org/abs/2211.02499).</p><p><a href="https://hackerpaper.kaipfister.de/p/2211.02499/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL