Moshi: a speech-text foundation model for real-time dialogue
Paper • 2410.00037 • Published • 14
Moshi v0.1 Release
MLX, Candle & PyTorch model checkpoints released as part of the Moshi release from Kyutai. Run inference via: https://github.com/kyutai-labs/moshi
-
-
kyutai/moshiko-pytorch-bf16
Updated • 165k • 238 -
kyutai/moshika-pytorch-bf16
Updated • 1.85k • 60 -
kyutai/mimi
Feature Extraction • 96.2M • Updated • 1.32M • • 295 -
kyutai/moshiko-mlx-q4
Updated • 996 • 29 -
kyutai/moshika-mlx-q4
Updated • 210 • 14 -
kyutai/moshiko-mlx-q8
Updated • 1.93k • 5 -
kyutai/moshika-mlx-q8
Updated • 110 • 8 -
kyutai/moshiko-mlx-bf16
Updated • 170 • 9 -
kyutai/moshika-mlx-bf16
Updated • 50 • 11 -
kyutai/moshiko-candle-q8
8B • Updated • 19.8k • 18 -
kyutai/moshika-candle-q8
8B • Updated • 1.64k • 14 -
kyutai/moshiko-candle-bf16
Updated • 587 • 14 -
kyutai/moshika-candle-bf16
Updated • 268 • 4 -
kyutai/moshiko-pytorch-q8
Updated • 1.47k • 3 -
kyutai/moshika-pytorch-q8
Updated • 242 • 3