Patrick Pérez

Unmute adds ears and vocal chords to your favorite text-based language model. A seamless plug-and-play augmentation with easy personalisation through voice conditioning and text instructions. We will open-source shortly.

24.05.2025 08:06 — 👍 12    🔁 3    💬 0    📌 0

After its preview version in last January, Helium 1 now takes its full expanse, with 2 billions of well used open parameters. 🇧🇬 🇭🇷 🇨🇿 🇩🇰 🇳🇱 🇬🇧 🇪🇪 🇫🇮 🇫🇷 🇩🇪 🇬🇷 🇭🇺 🇮🇪 🇮🇹 🇱🇻 🇱🇹 🇲🇹 🇵🇱 🇵🇹 🇷🇴 🇸🇰 🇸🇮 🇪🇸 🇸🇪

07.05.2025 22:34 — 👍 4    🔁 0    💬 0    📌 0

One vertu of open models is to allow one to adapt them to one’s needs. This is even more impactful when finetuning is data- and compute-efficient. This is something we strive for at Kyutai. Let’s start with Moshi, our groundbreaking multi-stream spoken dialogue model.

02.04.2025 10:28 — 👍 2    🔁 0    💬 0    📌 0

🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷

Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...

Big 🧵👇 with details!

21.03.2025 06:43 — 👍 137    🔁 51    💬 8    📌 10

Diplomacy dies on live TV as Trump and Vance gang up to bully Ukraine leader US president said his horrific blow-up would make ‘great television’ – the White House has never seen anything like it

I wish it is a disgraceful video generated by an unhinged AI. Unfortunately, it is the disgraceful new reality. Shame on Trump and Vance.
www.theguardian.com/us-news/2025...

01.03.2025 09:13 — 👍 4    🔁 0    💬 0    📌 0

Pushing testing dedication to the next level.

11.02.2025 23:40 — 👍 5    🔁 0    💬 0    📌 0

Simultaneous speech-to-speech translation on mobile is a world premiere. In the near future, no one will ever be lost in translation (at least for linguistic reasons).

10.02.2025 22:14 — 👍 7    🔁 1    💬 0    📌 0

New sharing step on our journey towards easy-to-use fully-open models.

16.01.2025 10:44 — 👍 15    🔁 7    💬 0    📌 0