kyutai-labs/hibiki

Hibiki is a model for streaming speech translation (also known as simultaneous translation). Unlike offline translation—where one waits for the end of the source utterance to start translating--- Hibiki adapts its flow to accumulate just enough context to produce a correct translation in real-time, chunk by chunk.

5 best points · 1 comments · 1 Hacker News post · 1,537 GitHub stars · View on GitHub

Hacker News discussions

• Hibiki: High-Fidelity Simultaneous Speech-to-Speech Translation (5 points, 1 comments, by Philpax, 2025-02-06)