SSealbook
Sealbook / Open source / Machine learning y ciencia de datos

kyutai-labs/moshi

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

GitHub ↗

Licencia y mantenimiento

Apache-2.0 es una licencia permisiva: uso comercial libre con atribución.

Último cambio de código hace 39 días.

Proyectos similares

RepositorioEstrellasLenguajeLicenciaActividad
1openclaw/openclawThe AI that really does things. Any OS. Any Platform. The lobster way. 🦞 ★ 392.4kTypeScriptMITActivo
2tensorflow/tensorflowAn Open Source Machine Learning Framework for Everyone★ 201.1kC++Apache-2.0Activo
3AUTOMATIC1111/stable-diffusion-webuiStable Diffusion web UI★ 165.1kPythonAGPL-3.0Menos activo
4Comfy-Org/ComfyUIThe most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the w★ 138.4kPythonGPL-3.0Activo
5openai/whisperRobust Speech Recognition via Large-Scale Weak Supervision★ 110.8kPythonMITActivo
6pytorch/pytorchTensors and Dynamic neural networks in Python with strong GPU acceleration★ 104.8kPythonOtherActivo
7hacksider/Deep-Live-Camreal time face swap and one-click video deepfake with only a single image★ 97.1kPythonAGPL-3.0Activo
8odysseus-dev/odysseusSelf-hosted AI workspace. ★ 93.9kPythonAGPL-3.0Activo