←back to thread

High-fidelity simultaneous speech-to-speech translation

(arxiv.org)
112 points Bluestein | 1 comments | 03 Jul 25 20:27 UTC | HN request time: 0.417s | source
Show context
totetsu ◴[03 Jul 25 22:49 UTC] No.44459772[source]▶
All these Japanese project names and no Japanese support (ToT)
replies(2): >>44460938 #>>44463679 #
1. woodson ◴[04 Jul 25 03:31 UTC] No.44460938[source]▶
Check out this model based on the same architecture for Japanese: https://github.com/nu-dialogue/j-moshi