Streaming Translation and Transcription Through Speech-to-Text Causal Alignment

Excerpt

arXiv:2603.11578v2 Announce Type: replace Abstract: Simultaneous machine translation (SiMT) has traditionally relied on offline machine translation models coupled with human-engineered heuristics or learned policies. We propose Hikari, a policy-free, end-to-end model for simultaneous speech-to-text translation and streaming transcription. We also introduce Decoder Time Dilation, a mechanism that counteracts the overrepresentation of WAIT tokens in training. We present a supervised fine-tuning st