kyutai/pocket-tts
Updated • 1.13k • 1.3k
AI & ML interests
Our mission is to build and democratize artificial general intelligence through open science
Recent Activity
View all activity
Papers
MuScriptor: An Open Model for Multi-Instrument Music Transcription
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
kyutai/pocket-tts-without-voice-cloning
Updated • 13.6k • 38
kyutai/reki-2b
Robotics • 2B • Updated • 58 • 5
kyutai/reki-2b-robocasa365
Robotics • 2B • Updated • 41
kyutai/reki-2b-robotwin-cleanrand
Robotics • 2B • Updated • 29
kyutai/reki-2b-robotwin-clean
Robotics • 2B • Updated • 36
kyutai/reki-2b-libero
Robotics • 2B • Updated • 66 • 1
kyutai/ovie-ft-dl3dv
Image-to-Image • 0.1B • Updated • 43
kyutai/ovie-ft-re10k
Image-to-Image • 0.1B • Updated • 54
kyutai/ovie-512
Image-to-Image • 0.1B • Updated • 94
kyutai/ovie
Image-to-Image • 0.1B • Updated • 216 • 17
kyutai/glm-4-voice-of-reason-9b
Any-to-Any • 10B • Updated • 563 • 20
kyutai/glm-4-voice-of-reason-stitch-9b
Any-to-Any • 10B • Updated • 334 • 7
kyutai/CASA-Qwen2_5-VL-3B-LiveCC
Video-Text-to-Text • 4B • Updated • 2.46k • 6
kyutai/CASA-Qwen2_5-VL-3B
Image-Text-to-Text • 4B • Updated • 186 • 3
kyutai/Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 170 • 2
kyutai/CASA-Qwen2_5-VL-3B-Shared
Image-Text-to-Text • 4B • Updated • 56 • 1
kyutai/CASA-Helium1-VL-2B-Shared
Image-Text-to-Text • 3B • Updated • 31
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 161 • 10
kyutai/ARC4_Encoder_Llama
Feature Extraction • 3B • Updated • 2
kyutai/ARC8_Encoder_Mistral
Feature Extraction • 3B • Updated • 96 • 2
kyutai/ARC8_Encoder_multi
Feature Extraction • 3B • Updated • 149 • 7
kyutai/ARC8_Encoder_Llama
Feature Extraction • 3B • Updated • 101 • 3
kyutai/moshika-rl-seamless
Audio-to-Audio • 8B • Updated • 301 • 32
kyutai/personaplex-rl-seamless
Audio-to-Audio • 8B • Updated • 4.6k • 44
kyutai/Sequential_Helium_6B
Text Generation • 6B • Updated • 472 • 2
kyutai/moshi-rag-artifacts
Updated • 1
kyutai/moshika-rag-pytorch-bf16
Audio-to-Audio • 8B • Updated • 614 • 15
kyutai/moshika-rag-candle-bf16
Audio-to-Audio • 8B • Updated • 241 • 13
kyutai/tts-voices
Updated • 198