tipi/kyutai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Plug Unmute

Browse Source
This commit is contained in:
Václav Volhejn 2025-07-07 16:50:33 +02:00
parent c565c7ab6d
commit 55632edfb2
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -5,6 +5,7 @@ This repo contains instructions and examples of how to run
and [Kyutai Text-To-Speech](#kyutai-text-to-speech) models. and [Kyutai Text-To-Speech](#kyutai-text-to-speech) models.
These models are powered by delayed streams modeling (DSM), These models are powered by delayed streams modeling (DSM),
a flexible formulation for streaming, multimodal sequence-to-sequence learning. a flexible formulation for streaming, multimodal sequence-to-sequence learning.
See also [Unmute](https://github.com/kyutai-labs/unmute), an voice AI system built using Kyutai STT and Kyutai TTS.
But wait, what is "Delayed Streams Modeling"? It is a technique for solving many streaming X-to-Y tasks (with X, Y in `{speech, text}`) But wait, what is "Delayed Streams Modeling"? It is a technique for solving many streaming X-to-Y tasks (with X, Y in `{speech, text}`)
that formalize the approach we had with Moshi and Hibiki. A pre-print paper is coming soon! that formalize the approach we had with Moshi and Hibiki. A pre-print paper is coming soon!