Candle & PyTorch model checkpoints released as part of the MoshiRAG release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi-rag
Kyutai
non-profit
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
One View Is Enough! Monocular Training for In-the-Wild Novel View Generation
CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
spaces 5
Running
Agents
3
CASA Gallery
🏠
Video Gallery for CASA: Cross-Attention over Self-Attention
Running
11
Hibiki Zero Samples
🏆
Demo samples of the speech translation model Hibiki-Zero.
Running
6
CALM Samples
🤗
Running
1
Unmute Samples
💻
Examples of conversations with Unmute (unmute.sh)
Running
53
Hibiki Samples
🤗
Translate speech in real-time with high fidelity
models 66
kyutai/pocket-tts-without-voice-cloning
Updated • 23.1k • 24
kyutai/pocket-tts
Updated • 8.43k • 612
kyutai/moshi-rag-artifacts
Updated • 1
kyutai/moshika-rag-pytorch-bf16
Audio-to-Audio • Updated • 962 • 3
kyutai/moshika-rag-candle-bf16
Audio-to-Audio • Updated • 352 • 6
kyutai/ovie
Image-to-Image • Updated • 834 • 11
kyutai/ARC4_Encoder_Llama
Feature Extraction • Updated
kyutai/tts-voices
Updated • 148
kyutai/CASA-Helium1-VL-2B
Image-Text-to-Text • 3B • Updated • 11 • 8
kyutai/hibiki-zero-3b-pytorch-bf16
Audio-to-Audio • Updated • 2.96k • 51
datasets 7
kyutai/HaluEvalAudio_1000
Viewer • Updated • 1k • 124
kyutai/Audio-NTREX-4L
Viewer • Updated • 3.6k • 502 • 3
kyutai/librispeech_test_clean_enhanced
Viewer • Updated • 448 • 53 • 1
kyutai/ARC_finetuning
Preview • Updated • 18
kyutai/voices_tts_longeval
Viewer • Updated • 1.54k • 214 • 1
kyutai/DailyTalkContiguous
Preview • Updated • 1.51k • 19
kyutai/Babillage
Viewer • Updated • 465k • 249 • 13