🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

We just released the Helium-1 model , a 2B multi-lingual LLM which Edouard Grave and Laurent Mazare have been crafting for us! Best model so far under 2.17B params on multi-lingual benchmarks 🇬🇧🇮🇹🇪🇸🇵🇹🇫🇷🇩🇪 On HF, under CC-BY licence: huggingface.co/kyutai/helium-…

Helium 2B running locally on an iPhone 16 Pro at 28 tok/s, faster than you can read, all thanks to mlx-swift with q4 quantization!

Today we release Hibiki, real-time speech translation that runs on your phone. Adaptive flow without fancy policy, simple temperature sampling of a multistream audio-text LM. Very proud of Tom Labiausse 's work as an intern.

We just released Hibiki, a 🎙️-to-🔊 simultaneous translation model 🇫🇷🇬🇧 We leverage a large synthetic corpus synthesized from the text translation model MADLAD, and our own TTS + simple lag rule. Model is decoder only, runs at scale, even on device 📲 github.com/kyutai-labs/hi…

Afraid of missing out on French pop culture references because you don't speak the language? Fear no more and try our Hibiki speech-to-speech translation model— no more FOMO! 🇫🇷✨ #Translation #AI

Two new studies from our team we're particularly happy about Study 1: Brain-to-Text Decoding: ai.meta.com/research/publi… Study 2: From Thought to Action: ai.meta.com/research/publi… Blog: ai.meta.com/blog/brain-ai-…

Thanks to Xavier Niel for stopping by at the #AIActionSummit to try Hibiki. No need to struggle with English anymore 😅

I’ll be talking about our speech-to-speech framework that underpin Moshi and our recent live translation model Hibiki, this Wednesday 12th at 2:40pm at the MBZUAI workshop!

Very happy to have participated in this *beautiful* documentary from Florent Muller on the frontiers of humans and machine together with Yann LeCun Joelle Pineau Tom M Mitchell Alexandre Défossez and many more france.tv/documentaires/…

Great night hitting the club with Alexandre Défossez and Hibiki!

I'll present a dive into Moshi 🟢 and our translation model Hibiki 🇫🇷♻️🇬🇧 in the next Convai_rg reading group👨‍🏫📗. 📅 13/03 🕰️ 11am ET, 4pm in Paris. I'll discuss Mimi 🗜️ and multistream audio modeling 🔊. Join on Zoom, replay on YT. ⬛⬛🟧🟧🟨🟨🟩🟩🟩⬛ ⬛🟧🟧🟨🟨🟩🟩🟩⬛⬛

I haven't tested it yet, but those results looks really impressive, so nice that it is open source and medium sized.

What are we waiting for? 🤔

Just back from holidays, a bit late to announce MoshiVis, extending Moshi's capabilities to take in images 📷. Only 200M trainable weights to plug a vision encoder through cross attention🖼️🔀🎤 Training relies on a mix of text only and text+audio synthetic data (~20k hours) 💽

We just open sourced a fine tuning codebase for Moshi!

🚀 Thrilled to announce Helium 1, our new 2B-parameter LLM, now available alongside dactory, an open-source pipeline to reproduce its training dataset covering all 24 EU official languages. Helium sets new standards within its size class on European languages!

Talk to unmute.sh 🔊, the most modular voice AI around. Empower any text LLM with voice, instantly, by wrapping it with our new speech-to-text and text-to-speech. Any personality, any voice. Interruptible, smart turn-taking. We’ll open-source everything within the

Using Unmute with a custom voice and prompt to create a very intense ice cream seller, inspired by Justin Kuritzkes' sketch🍦