We just released unmute.sh 🔇🔊 It is a text LLM wrapper, based on in-house streaming ASR, TTS, semantic VAD to reduce latency. ⏱️ Unlike Moshi 🟢, Unmute 🔊 is turn base, but allows customization in two clicks🖱️: voice and prompt! Paper and open source coming soon.

We just open sourced a fine tuning codebase for Moshi!

Kyutai@kyutai-labs.bsky.social · 2y ago

Have you enjoyed talking to 🟢Moshi and dreamt of making your own speech to speech chat experience🧑‍🔬🤖? It's now possible with the moshi-finetune codebase! Plug your own dataset and change the voice/tone/personality of Moshi 💚🔌💿. An example after finetuning w/ only 20 hours of the DailyTalk dataset. 🧵

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

Kyutai@kyutai-labs.bsky.social · 2y ago

Meet MoshiVis🎙️🖼️, the first open-source real-time speech model that can talk about images! It sees, understands, and talks about images — naturally, and out loud. This opens up new applications, from audio description for the visual impaired to visual access to information.

I'll start my presentation in 10 minutes, you can join in Zoom: concordia-ca.zoom.us/j/81541793947 See you there!

Alexandre Défossez@honualx.bsky.social · 2y ago

I'll present a dive into Moshi 🟢 and our translation model Hibiki 🇫🇷♻️🇬🇧 as part of the next @convai-rg.bsky.social reading group 👨‍🏫📗. 📅 13th of March 🕰️ 11am ET, 4pm in Paris. I'll discuss Mimi 🗜️ and multi-stream audio modeling 🔊. Join on Zoom, replay on YT. ⬛ ⬛ 🟧 🟧 🟨 🟨 🟩 🟩 🟩 ⬛ ⬛ 🟧 🟧 🟨 🟨 🟩 🟩 🟩 ⬛ ⬛

I'll present a dive into Moshi 🟢 and our translation model Hibiki 🇫🇷♻️🇬🇧 as part of the next @convai-rg.bsky.social reading group 👨‍🏫📗. 📅 13th of March 🕰️ 11am ET, 4pm in Paris. I'll discuss Mimi 🗜️ and multi-stream audio modeling 🔊. Join on Zoom, replay on YT. ⬛ ⬛ 🟧 🟧 🟨 🟨 🟩 🟩 🟩 ⬛ ⬛ 🟧 🟧 🟨 🟨 🟩 🟩 🟩 ⬛ ⬛

@convai-rg.bsky.social · 2y ago

📢 Join our Conversational AI Reading Group! 📅 Thursday, March 13 | 11 AM - 12 PM EST 🎙Speaker: Alexandre Defossez 📖 Topic: "Moshi: a speech-text foundation model for real-time dialogue" 🔗 Details: (poonehmousavi.github.io/rg) ▶️ Missed a session? Watch on YouTube: (www.youtube.com/@CONVAI_RG) 🚀

Even Kavinsky 🎧🪩 can't break Hibiki! Just like Moshi, Hibiki is robust to extreme background conditions 💥🔊.

Very happy to have participated in this *beautiful* documentary from Florent Muller, on the frontiers between humans and machines, following next @yann-lecun.bsky.social and so many humbling figures of AI: www.france.tv/documentaire...

France TV - Replay et Direct tv des chaînes France Télévisions (ex Pluzz)

Retrouvez toutes les vidéos, articles et podcasts des programmes des chaînes de France Télévisions.

france.tv

Our latest studies on the decoding text from brain activity, reviewed by MIT Tech Review @technologyreview.com www.technologyreview.com/2025/02/07/1...

Check out our paper, with Lawrence Stewart and @bachfrancis.bsky.social Link: arxiv.org/abs/2502.02996 1/8

Building Bridges between Regression, Clustering, and Classification

Regression, the task of predicting a continuous scalar target y based on some features x is one of the most fundamental tasks in machine learning and statistics. It has been observed and...

arxiv.org

Excited to meet and exchange with a number of actors from all around the world at the AI Summit 🌍

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/hibiki

Kyutai@kyutai-labs.bsky.social · 2y ago

Meet Hibiki, our simultaneous speech-to-speech translation model, currently supporting 🇫🇷➡️🇬🇧. Hibiki produces spoken and text translations of the input speech in real-time, while preserving the speaker’s voice and optimally adapting its pace based on the semantic content of the source speech. 🧵

🚨Job alert (Please RT) What: masters internship and/or PhD positions Where: Rothschild Foundation Hospital (Paris, France) Topic: AI and Neuroscience Supervised by: Pierre Bourdillon and myself Apply here: forms.gle/KKnea2QAjhAe... Deadline: Feb 5th

We just released the Helium-1 model , a 2B multi-lingual LLM which @exgrv.bsky.social and @lmazare.bsky.social 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/heliu...

Kyutai@kyutai-labs.bsky.social · 2y ago

Meet Helium-1 preview, our 2B multi-lingual LLM, targeting edge and mobile devices, released under a CC-BY license. Start building with it today! huggingface.co/kyutai/heliu...