kyutai/ARC4_Encoder_Llama
Feature Extraction • 3B • Updated • 2
AI & ML interests
Our mission is to build and democratize artificial general intelligence through open science
Recent Activity
Papers
MuScriptor: An Open Model for Multi-Instrument Music Transcription
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
kyutai/ARC8_Encoder_Mistral
Feature Extraction • 3B • Updated • 35 • 2
kyutai/ARC8_Encoder_multi
Feature Extraction • 3B • Updated • 21 • 7
kyutai/ARC8_Encoder_Llama
Feature Extraction • 3B • Updated • 24 • 3
kyutai/moshika-rl-seamless
Audio-to-Audio • 8B • Updated • 142 • 30
kyutai/personaplex-rl-seamless
Audio-to-Audio • 8B • Updated • 11.8k • 33
kyutai/Sequential_Helium_6B
Text Generation • 6B • Updated • 145 • 2
kyutai/pocket-tts-without-voice-cloning
Updated • 5.91k • 30
kyutai/pocket-tts
Updated • 1.37k • 768
kyutai/moshi-rag-artifacts
Updated • 1
kyutai/moshika-rag-pytorch-bf16
Audio-to-Audio • 8B • Updated • 2.18k • 13
kyutai/moshika-rag-candle-bf16
Audio-to-Audio • 8B • Updated • 237 • 12
kyutai/ovie
Image-to-Image • 0.1B • Updated • 185 • 16
kyutai/tts-voices
Updated • 170
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 23 • 9
kyutai/hibiki-zero-3b-pytorch-bf16
Audio-to-Audio • Updated • 1.45k • 56
kyutai/CASA-Qwen2_5-VL-3B-LiveCC
Video-Text-to-Text • 4B • Updated • 18 • 5
kyutai/Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 21 • 2
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 21 • 3
kyutai/stt-1b-en_fr
Automatic Speech Recognition • 1.0B • Updated • 135
kyutai/tts-0.75b-en-public
Text-to-Speech • Updated • 1.07k • 17
kyutai/tts-1.6b-en_fr
Text-to-Speech • Updated • 62k • 378
kyutai/stt-1b-en_fr-candle
Automatic Speech Recognition • 1.0B • Updated • 9
kyutai/mimi
Feature Extraction • 96.2M • Updated • 797k • • 318
kyutai/stt-2.6b-en
Automatic Speech Recognition • 3B • Updated • 124
kyutai/stt-1b-en_fr-trfs
Automatic Speech Recognition • 1B • Updated • 1.29k • 13
kyutai/stt-2.6b-en-trfs
Automatic Speech Recognition • 3B • Updated • 9.26k • 10
kyutai/stt-1b-en_fr-mlx
Automatic Speech Recognition • 1.0B • Updated • 6
kyutai/stt-2.6b-en-candle
Automatic Speech Recognition • 3B • Updated • 3
kyutai/stt-2.6b-en-mlx
Automatic Speech Recognition • 3B • Updated • 9