rust/delayed-streams-modeling
1
0
Fork 0
mirror of https://github.com/kyutai-labs/delayed-streams-modeling.git synced 2025-12-23 03:19:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Replace "pre-print coming soon"

Browse Source
This commit is contained in:
Vaclav Volhejn
2025-09-11 13:00:03 +02:00
parent f741fc473f
commit 22e0b400e8
1 changed files with 1 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -3,12 +3,10 @@
This repo contains instructions and examples of how to run
[Kyutai Speech-To-Text](#kyutai-speech-to-text)
and [Kyutai Text-To-Speech](#kyutai-text-to-speech) models.
These models are powered by delayed streams modeling (DSM),
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}`)
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. See our [pre-print about DSM](https://arxiv.org/abs/2509.08753).
## Kyutai Speech-To-Text