From 843f63bfec9b878716026173b6b1e4d68cf3c65d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Alexandre=20D=C3=A9fossez?= Date: Wed, 18 Sep 2024 16:48:03 +0200 Subject: [PATCH] Update README.md --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 021e6d8..15ba714 100644 --- a/README.md +++ b/README.md @@ -3,6 +3,8 @@ ![precommit badge](https://github.com/kyutai-labs/moshi/workflows/precommit/badge.svg) ![rust ci badge](https://github.com/kyutai-labs/moshi/workflows/Rust%20CI/badge.svg) +[[Read the paper]][moshi] [[Demo]](https://moshi.chat) + [Moshi][moshi] is a speech-text foundation model and **full-duplex** spoken dialogue framework. It uses [Mimi][moshi], a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size),